© 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. 23957
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uffed
    -0.27
    ston
    -0.26
     blot
    -0.25
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.24
    IJľç´¢
    -0.24
    èľļ
    -0.24
    oron
    -0.24
    ITIONS
    -0.24
    iol
    -0.24
    `);↵
    -0.23
    POSITIVE LOGITS
    æł·
    0.30
    placeholders
    0.26
    Å¡e
    0.26
    cheme
    0.25
    ä¸īçĤ¹
    0.24
    åįģåħ«
    0.24
    æĺ¯æ²¡æľī
    0.24
    å¤Ħå¤Ħ
    0.23
     interviewer
    0.23
    GRP
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.