© 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. 32-TRANSCODER-HP
    7. 41734
    Prev
    Next
    INDEX
    Explanations

    medical/scientific reports

    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
    两åı¥
    -0.41
    两
    -0.37
    two
    -0.36
     Two
    -0.35
     TWO
    -0.33
    两个
    -0.33
    两款
    -0.33
     deux
    -0.33
    Two
    -0.33
     two
    -0.32
    POSITIVE LOGITS
     only
    0.34
    olland
    0.28
    Fn
    0.27
    roducing
    0.26
    Only
    0.26
     Only
    0.25
    ừa
    0.25
     just
    0.25
    åľ¬
    0.25
    çŃĶçĸij
    0.25
    Activations Density 0.003%

    No Known Activations