© 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. 32-TRANSCODER-HP
    7. 41156
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eros
    -0.27
    chner
    -0.26
    )obj
    -0.25
    inke
    -0.25
    imin
    -0.25
    ink
    -0.25
     coax
    -0.25
    ustry
    -0.25
    ELY
    -0.24
     brid
    -0.24
    POSITIVE LOGITS
    æ°´åĩĨ
    0.35
     treatment
    0.31
    æ²»çĸĹ
    0.30
    æ°´å¹³
    0.28
    çļĦéľĢæ±Ĥ
    0.28
    ä»·ä½į
    0.28
     treatments
    0.28
    needs
    0.27
     needs
    0.27
     Diff
    0.27
    Activations Density 0.001%

    No Known Activations