© 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. 23-TRANSCODER-HP
    7. 24764
    Prev
    Next
    INDEX
    Explanations

    Uncertainty, possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为主线
    -0.29
    chers
    -0.25
    /String
    -0.24
    Collections
    -0.23
    cek
    -0.23
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.23
    ç»į
    -0.23
    没èĥ½
    -0.23
     EITHER
    -0.22
    icians
    -0.22
    POSITIVE LOGITS
    çĶļèĩ³
    1.53
     even
    1.38
    çĶļèĩ³è¿ĺ
    1.34
    çĶļèĩ³æĺ¯
    1.18
    even
    1.16
     sogar
    1.13
     Even
    1.05
    Even
    1.04
     даже
    1.02
    çĶļèĩ³è¿ŀ
    0.95
    Activations Density 0.005%

    No Known Activations