© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25919
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pem
    -0.07
    mant
    -0.07
    .↵
    -0.07
    нию
    -0.07
    这一点
    -0.07
    Raised
    -0.07
     simulator
    -0.07
    ppt
    -0.06
     contestants
    -0.06
    ).↵
    -0.06
    POSITIVE LOGITS
    海关
    0.08
    (Output
    0.08
    ᅧ
    0.08
     GraphQL
    0.07
    \Factory
    0.07
    Ổ
    0.07
    }}>
    0.07
    >Email
    0.07
    ÂN
    0.07
     ContentType
    0.07
    Activations Density 0.593%

    No Known Activations