© 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. 14-TRANSCODER-HP
    7. 40035
    Prev
    Next
    INDEX
    Explanations

    some text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥Ĺ
    -0.28
    ocop
    -0.27
    Tween
    -0.26
    ä¸įå¼Ģ
    -0.25
     Tactical
    -0.25
    forme
    -0.25
    formed
    -0.25
     Qty
    -0.23
     packageName
    -0.23
    ãĤ§
    -0.23
    POSITIVE LOGITS
    éĿĵ
    0.29
    éŃħåĬĽ
    0.25
     latest
    0.25
    ForObject
    0.25
    ">\
    0.25
     te
    0.25
    ÑĩиÑĤ
    0.24
    åĦĨ
    0.24
    cee
    0.24
     incorpor
    0.24
    Activations Density 1.329%

    No Known Activations