© 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. 41830
    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
    ÃŃst
    -0.27
    hotmail
    -0.27
    etical
    -0.26
    (seg
    -0.26
    ستر
    -0.26
    arming
    -0.25
     ost
    -0.25
     tet
    -0.25
    ist
    -0.24
     dad
    -0.24
    POSITIVE LOGITS
     Social
    0.42
     social
    0.41
    Social
    0.40
    _social
    0.37
    social
    0.35
    åĴĮ社ä¼ļ
    0.34
    -social
    0.34
    社ä¼ļ
    0.33
    æĢ§
    0.33
     socio
    0.33
    Activations Density 0.006%

    No Known Activations