© 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. 15-RESID-POST-AA
    6. 14713
    Prev
    Next
    INDEX
    Explanations

    completion, ending, process

    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
    сто
    -0.07
    emos
    -0.07
     Philip
    -0.07
    .cont
    -0.07
    帶
    -0.06
    veloper
    -0.06
    .flip
    -0.06
     ano
    -0.06
     spe
    -0.06
    社区
    -0.06
    POSITIVE LOGITS
    溵
    0.07
    влажн
    0.07
    偎
    0.07
    ฝน
    0.07
    cancellationToken
    0.07
    腑
    0.07
    _CONNECTION
    0.07
    _EXIST
    0.07
    	rt
    0.07
    取证
    0.06
    Activations Density 0.157%

    No Known Activations