© 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. 20-TRANSCODER-HP
    7. 107205
    Prev
    Next
    INDEX
    Explanations

    ordering or position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.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¸ĩåħĥ以ä¸Ĭ
    -0.28
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.27
    æĪª
    -0.27
     marker
    -0.27
    天ä¸Ĭ
    -0.27
    atter
    -0.26
    ä¸Ńå¤ĸ
    -0.26
    æ¸į
    -0.26
    -marker
    -0.25
     mitt
    -0.25
    POSITIVE LOGITS
    è¾ĺ
    0.29
     Floors
    0.28
     or
    0.27
    yat
    0.27
     конкÑĥÑĢÑģ
    0.26
     или
    0.26
    æĪĸ
    0.25
    åı¯è§Ĩ
    0.25
    æĪĸèĢħ
    0.25
    ichtig
    0.25
    Activations Density 51.693%

    No Known Activations