© 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. 24-TRANSCODER-HP
    7. 149717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slut
    -0.30
    adem
    -0.29
    apot
    -0.28
     emptied
    -0.27
    .generated
    -0.26
    çĸ¤
    -0.25
     Piece
    -0.25
    xEC
    -0.24
    éĹ°
    -0.24
    -piece
    -0.24
    POSITIVE LOGITS
    ling
    0.29
    ä¸ĢæĬĬ
    0.27
    æľ¬èº«å°±æĺ¯
    0.26
    å°ıåĮº
    0.26
    微信åħ¬ä¼Ĺ
    0.26
    æĵĤ
    0.25
    ä¹±
    0.25
    ning
    0.25
    æ·«
    0.24
    ningen
    0.24
    Activations Density 0.301%

    No Known Activations

    This feature has no known activations.