© 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. 19-RESID-POST-AA
    11. 68936
    Prev
    Next
    INDEX
    Explanations

    A

    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
     ú
    -0.08
     chắc
    -0.07
    abbo
    -0.07
    .JButton
    -0.07
    祼
    -0.07
    .rar
    -0.07
    愀
    -0.07
    �
    -0.07
    橛
    -0.06
    ант
    -0.06
    POSITIVE LOGITS
    unsafe
    0.08
     первую
    0.07
     expansion
    0.07
    /pm
    0.07
    _reward
    0.07
    Unsafe
    0.07
    财经
    0.06
    .index
    0.06
    อะไร
    0.06
    调研
    0.06
    Activations Density 0.006%

    No Known Activations