© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6330
    Prev
    Next
    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosk
    -0.25
    ersen
    -0.25
    åľ¨æĹ¥æľ¬
    -0.24
     Rim
    -0.23
     minded
    -0.21
    Enumerable
    -0.21
     FORE
    -0.21
    æ¡Ĩ
    -0.21
    çĦ¶æĺ¯
    -0.21
    ä½Ļ人
    -0.21
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.26
    oth
    0.25
    sen
    0.24
     limiting
    0.24
    fully
    0.24
    ful
    0.24
    Beer
    0.23
    oen
    0.23
    Asked
    0.23
     IK
    0.23
    Activations Density 0.951%

    No Known Activations