© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21259
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash

    sentences that give advice or strong recommendations (conclusive, directive statements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    のではないか
    -0.08
    党的建设
    -0.08
    }else
    -0.07
    .localStorage
    -0.07
    ën
    -0.07
    localStorage
    -0.07
    ın
    -0.07
    lemen
    -0.07
    stateParams
    -0.07
     aynı
    -0.07
    POSITIVE LOGITS
    멜
    0.07
    谖
    0.07
    ヌ
    0.06
    +'&
    0.06
     gek
    0.06
    新产品
    0.06
    bek
    0.06
    ठ
    0.06
    젱
    0.06
    挂
    0.06
    Activations Density 0.313%

    No Known Activations