© 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. 18167
    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
    ImageSharp
    -0.27
    ency
    -0.26
    [:
    -0.26
    à¤Ī
    -0.25
    usher
    -0.25
    综åIJĪ
    -0.25
    æŀ«
    -0.25
     Conor
    -0.24
     equity
    -0.24
    ilers
    -0.23
    POSITIVE LOGITS
     bounced
    0.26
    ement
    0.26
    _ment
    0.26
    æ¦Ĥ念
    0.25
    çļĦæ¦Ĥ念
    0.25
    åģļæĪIJ
    0.24
     mitt
    0.24
    ements
    0.24
    大家åĪĨ享
    0.24
    åľ°ä½į
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.