© 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. 31-TRANSCODER-HP
    7. 19340
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨãĥ³
    -0.30
    èĭ£
    -0.28
    æŃ³
    -0.24
    воз
    -0.24
    ..<
    -0.24
    åĨħ
    -0.24
    -rest
    -0.23
     WrocÅĤaw
    -0.23
    ä¾ij
    -0.23
    orsi
    -0.23
    POSITIVE LOGITS
    atform
    0.33
    ä¸ĭ游
    0.28
    Fx
    0.27
     upstream
    0.27
    _dur
    0.26
     revolution
    0.26
     sustainability
    0.25
    æĹ¶è¡¨ç¤º
    0.25
    -series
    0.25
    ilon
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.