© 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. 24891
    Prev
    Next
    INDEX
    Explanations

    hypertrophy

    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
     lul
    -0.27
    æĪĺçķ¥å¸ĥå±Ģ
    -0.27
    éĹ®è¯¢
    -0.25
    åıijçİ°éĹ®é¢ĺ
    -0.25
    rary
    -0.25
    usted
    -0.25
     guides
    -0.25
    hints
    -0.25
    ãģªãģĦãģ®ãģ§
    -0.24
     exited
    -0.24
    POSITIVE LOGITS
    laÅŁ
    0.26
    éĢ¸
    0.24
    æĺ¯ä¸ĢåIJį
    0.24
     Hayward
    0.24
    >[]
    0.24
    SEA
    0.24
    (Bit
    0.23
    //[
    0.23
     wallpapers
    0.23
    	Name
    0.23
    Activations Density 0.002%

    No Known Activations