© 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. 33-TRANSCODER-HP
    7. 52842
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internally
    -0.26
     ref
    -0.26
     internal
    -0.26
     gest
    -0.26
    	UN
    -0.26
    UF
    -0.26
    OF
    -0.26
    riends
    -0.25
     unp
    -0.25
    :+
    -0.25
    POSITIVE LOGITS
    éĢIJ
    0.28
    kbd
    0.26
    è¯ł
    0.24
    éĢĨè¡Į
    0.24
     rebound
    0.24
    fol
    0.23
    é¢Ĩè·ij
    0.23
     ÄIJức
    0.23
     wol
    0.23
    ersistence
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.