© 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. 31-TRANSCODER-HP
    7. 18632
    Prev
    Next
    INDEX
    Explanations

    Current Events/Political Affairs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sullivan
    -0.28
    bserv
    -0.25
     Bris
    -0.25
     Sanctuary
    -0.24
    tracked
    -0.24
     inverse
    -0.24
    Ral
    -0.24
     invers
    -0.23
    æŃ»
    -0.23
    è´Łæĭħ
    -0.23
    POSITIVE LOGITS
     Christ
    0.30
    Christ
    0.29
    beits
    0.28
     abi
    0.27
    chia
    0.27
    ahr
    0.26
    ogo
    0.26
    oba
    0.26
    åĻªéŁ³
    0.26
    /temp
    0.25
    Activations Density 0.058%

    No Known Activations