© 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. 18747
    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
     pul
    -0.25
    缺
    -0.25
    mq
    -0.25
     Ti
    -0.25
    åħ³éĶ®
    -0.24
     bi
    -0.23
    Ti
    -0.23
    æľįåĬ¡ä½ĵç³»
    -0.23
     lado
    -0.23
    Bi
    -0.23
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.26
     endwhile
    0.25
    icit
    0.24
     caliber
    0.24
    offs
    0.24
    å°ıéķĩ
    0.24
    åħ¨éķĩ
    0.24
    assage
    0.24
    è§ģè¿ĩ
    0.24
    cir
    0.23
    Activations Density 10.409%

    No Known Activations

    This feature has no known activations.