© 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. 24-TRANSCODER-HP
    7. 149757
    Prev
    Next
    INDEX
    Explanations

    programming and software context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĭæĸ¹
    -0.26
    elog
    -0.25
    ä¸ĭéĿ¢
    -0.25
    ä¸ĭåİ»
    -0.24
     Installed
    -0.24
     below
    -0.24
     terminating
    -0.24
    ãĥĢãĤ¦ãĥ³
    -0.24
    installed
    -0.24
    hcp
    -0.24
    POSITIVE LOGITS
    omer
    0.26
    ç¬Ļ
    0.25
    èĥŀ
    0.24
    amping
    0.24
     authored
    0.24
    _ENCODE
    0.23
    ấu
    0.23
    Ẩ
    0.23
    actories
    0.23
    org
    0.23
    Activations Density 0.381%

    No Known Activations