© 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. 24636
    Prev
    Next
    INDEX
    Explanations

    variant

    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
    澳大利亚
    -0.09
     seulement
    -0.08
     shrinking
    -0.07
    illet
    -0.07
    полнение
    -0.07
     antioxidant
    -0.07
     Shield
    -0.07
    ではありません
    -0.07
    的原因
    -0.07
    选用
    -0.07
    POSITIVE LOGITS
     loggedIn
    0.08
    phans
    0.08
     paradigm
    0.07
     Респ
    0.07
     evento
    0.07
     azi
    0.07
     처리
    0.07
    awe
    0.07
     mensajes
    0.07
    ráf
    0.07
    Activations Density 0.000%

    No Known Activations