© 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. 108311
    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
     desc
    -0.30
    éĽ¢
    -0.29
    -turn
    -0.29
     turn
    -0.27
    ASC
    -0.27
     turns
    -0.26
    ars
    -0.26
    离
    -0.26
    ison
    -0.25
     turned
    -0.25
    POSITIVE LOGITS
    trand
    0.29
    人éĢī
    0.29
    ¤í
    0.26
    -Version
    0.25
    ç±³åħ°
    0.25
     econ
    0.25
    æ§
    0.25
     CDDL
    0.24
    æ¥ŀ
    0.24
    å¦Ĥæŀľçݩ家
    0.24
    Activations Density 1.016%

    No Known Activations

    This feature has no known activations.