© 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. 25-TRANSCODER-HP
    7. 108435
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĺ¿æĭī伯
    -0.29
    çīĩåŃIJ
    -0.27
    onical
    -0.26
    第ä¸ĢæĿ¡
    -0.26
    精度
    -0.26
    å´ĩé«ĺ
    -0.25
    å¼¹
    -0.25
    ETO
    -0.25
     Almighty
    -0.24
    ainty
    -0.24
    POSITIVE LOGITS
     part
    0.30
    éĥ¨åĪĨ
    0.29
    us
    0.28
    AccessException
    0.27
    è¿Ļéĥ¨åĪĨ
    0.26
    erator
    0.26
     gym
    0.25
     bis
    0.24
    ité
    0.24
     gy
    0.23
    Activations Density 0.961%

    No Known Activations

    This feature has no known activations.