© 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. 18774
    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
    .pr
    -0.28
    roke
    -0.28
    头èĦij
    -0.27
     fronts
    -0.27
    åĪ»
    -0.26
    _front
    -0.25
    åŃĹåı·
    -0.25
    _bp
    -0.25
    BAD
    -0.25
     front
    -0.25
    POSITIVE LOGITS
    å¤Ħå¤Ħéķ¿
    0.26
    ç»ĵæŀĦæĢ§
    0.26
    ì¶ľ
    0.25
     radio
    0.25
     Sax
    0.25
    .Concat
    0.24
    æľĢåıĹ欢è¿İ
    0.24
    (Boolean
    0.24
     erb
    0.23
    rtype
    0.23
    Activations Density 0.884%

    No Known Activations

    This feature has no known activations.