© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19646
    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
     Through
    -0.38
    Through
    -0.38
     through
    -0.32
    through
    -0.31
    éĢļè¿ĩ
    -0.31
     ÑĩеÑĢез
    -0.31
    _through
    -0.29
    sis
    -0.28
    åı¯éĢļè¿ĩ
    -0.28
     THROUGH
    -0.27
    POSITIVE LOGITS
     pass
    0.48
    pass
    0.43
    _pass
    0.41
    -pass
    0.41
    Pass
    0.40
    	pass
    0.38
     Pass
    0.38
     passes
    0.37
     passed
    0.37
    _PASS
    0.37
    Activations Density 0.541%

    No Known Activations

    This feature has no known activations.