© 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. 7-RESID-POST-AA
    11. 9622
    Prev
    Next
    INDEX
    Explanations

    Mises

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engine
    -0.07
     Address
    -0.07
    _interest
    -0.07
     đỉnh
    -0.06
     Expo
    -0.06
    บรรยากาศ
    -0.06
    옻
    -0.06
    .Mock
    -0.06
    难题
    -0.06
     eins
    -0.06
    POSITIVE LOGITS
    鼫
    0.07
    馒
    0.07
    荖
    0.07
    殒
    0.06
     ifs
    0.06
    ows
    0.06
    意义上的
    0.06
     adapt
    0.06
     playful
    0.06
    وثائق
    0.06
    Activations Density 0.094%

    No Known Activations