© 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. 41666
    Prev
    Next
    INDEX
    Explanations

    ethyl

    np_max-act · gemini-2.0-flash
    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
     advises
    -0.08
    ][(
    -0.07
     onActivityResult
    -0.07
    ingt
    -0.07
     crimes
    -0.07
    ARR
    -0.07
    放假
    -0.07
     fantasies
    -0.06
    heels
    -0.06
    ];//
    -0.06
    POSITIVE LOGITS
    glob
    0.07
    钔
    0.07
    .ref
    0.07
    ément
    0.07
     sniper
    0.07
    鲫
    0.07
    (man
    0.07
    (content
    0.07
    センター
    0.07
    크
    0.07
    Activations Density 0.004%

    No Known Activations