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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 1855
    Prev
    Next
    INDEX
    Explanations

    scientific and medical research

    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
    (cube
    -0.07
     porte
    -0.07
    Nova
    -0.07
    นม
    -0.06
     steroids
    -0.06
    菩
    -0.06
    rors
    -0.06
     Xm
    -0.06
     Carnival
    -0.06
     Decorating
    -0.06
    POSITIVE LOGITS
    记住
    0.07
    _country
    0.07
    )}
    ↵
    0.07
    span
    0.07
     cin
    0.07
    找到
    0.07
    -script
    0.07
    rowad
    0.07
    .assertEqual
    0.07
    쥑
    0.07
    Activations Density 0.546%

    No Known Activations