© 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. 19224
    Prev
    Next
    INDEX
    Explanations

    references

    np_max-act-logits · gemini-2.0-flash
    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
    伶
    -0.30
    æľ´ç´ł
    -0.27
     recognition
    -0.27
    /doc
    -0.26
    ä¸Ģ身
    -0.26
     recognizing
    -0.25
    лÑİÑĩ
    -0.25
    ]interface
    -0.25
    -purpose
    -0.25
    imbledon
    -0.24
    POSITIVE LOGITS
     refer
    0.34
     References
    0.33
    Ļ¶
    0.32
     refers
    0.32
     Refer
    0.32
     Reference
    0.32
    _references
    0.31
     referring
    0.31
     references
    0.30
     REFER
    0.30
    Activations Density 1.897%

    No Known Activations