Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71946
    Prev
    Next
    INDEX
    Explanations

    code/file instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .SingleOrDefault
    -0.07
    婼
    -0.07
    男神
    -0.07
    的结果
    -0.07
    沃尔沃
    -0.07
    hire
    -0.07
     steam
    -0.07
    氨基酸
    -0.07
    ﭰ
    -0.06
     öld
    -0.06
    POSITIVE LOGITS
     Knowing
    0.07
     prayers
    0.07
    -ra
    0.07
     Handle
    0.07
    Basic
    0.07
     FETCH
    0.07
     să
    0.07
    เก
    0.07
     Vari
    0.07
    Ready
    0.07
    Activations Density 0.107%

    No Known Activations