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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42389
    Prev
    Next
    INDEX
    Explanations

    social

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regulation
    -0.28
    æŁľ
    -0.26
    oggles
    -0.26
    etable
    -0.25
    å¸ĤåľºçĽij管
    -0.25
    usan
    -0.25
    ollapse
    -0.24
    eler
    -0.24
    LETE
    -0.24
    ords
    -0.24
    POSITIVE LOGITS
     social
    0.40
    åĴĮ社ä¼ļ
    0.33
     Social
    0.30
     sociale
    0.30
    social
    0.28
    _social
    0.28
    社ä¼ļ
    0.28
    Social
    0.28
    ernity
    0.27
     system
    0.27
    Activations Density 0.001%

    No Known Activations