© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 85066
    Prev
    Next
    INDEX
    Explanations

    UN Security Council/Iran/nuclear

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    很喜欢
    -0.07
     parental
    -0.07
     sofa
    -0.07
    月饼
    -0.07
     erv
    -0.07
     rotor
    -0.07
    国有企业
    -0.07
    ropical
    -0.07
    萝
    -0.07
    秋冬
    -0.07
    POSITIVE LOGITS
     passing
    0.07
     ********
    0.07
    _submission
    0.07
    FOUND
    0.07
     japanese
    0.07
    registered
    0.07
    _gc
    0.07
    .checked
    0.06
     preparedStatement
    0.06
     extra
    0.06
    Activations Density 0.029%

    No Known Activations