© 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. 108579
    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
    ITOR
    -0.27
    æĹ¥æĬ¥è®°èĢħ
    -0.26
    åľī
    -0.25
     face
    -0.25
     bat
    -0.25
     two
    -0.25
    ameda
    -0.24
     preparation
    -0.24
    两大
    -0.24
     retros
    -0.23
    POSITIVE LOGITS
    太æŀģ
    0.30
    lington
    0.30
    æĶ¾å¤§
    0.26
     getIntent
    0.25
    edList
    0.25
    icum
    0.24
    åĿŀ
    0.24
    é¦Ļæ°Ķ
    0.24
    为人
    0.24
    itelist
    0.23
    Activations Density 0.060%

    No Known Activations

    This feature has no known activations.