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. 109754
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
     вы
    -0.08
     isempty
    -0.07
     learning
    -0.07
     ראש
    -0.07
     preferredStyle
    -0.07
     strncmp
    -0.07
     Ordered
    -0.07
    Donate
    -0.07
     guide
    -0.06
    试
    -0.06
    POSITIVE LOGITS
    됨
    0.08
    非常适合
    0.07
    SHA
    0.07
    这是一个
    0.07
     crippling
    0.07
     bombed
    0.07
    굿
    0.07
    ;"><?
    0.07
    GMT
    0.06
    いたします
    0.06
    Activations Density 0.092%

    No Known Activations