© 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. 108975
    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
    otos
    -0.26
    iev
    -0.26
     conf
    -0.25
     borr
    -0.25
    æ·ĸ
    -0.25
     bö
    -0.24
    evin
    -0.24
    earn
    -0.24
     diamond
    -0.24
    ellaneous
    -0.23
    POSITIVE LOGITS
    æľĪèĩ³
    0.28
    ä»Ĭ天æĪij们
    0.26
     catcher
    0.25
    anta
    0.24
    éĩĮéĿ¢æľī
    0.23
    ose
    0.23
    packing
    0.23
     IPC
    0.23
    lux
    0.23
    çĺ´
    0.23
    Activations Density 0.894%

    No Known Activations

    This feature has no known activations.