© 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. 43286
    Prev
    Next
    INDEX
    Explanations

    Medical or related associations

    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
    ptive
    -0.33
    太åIJİ
    -0.32
     ace
    -0.31
    åĢ®
    -0.27
    gia
    -0.27
     processor
    -0.27
    ÃĸZ
    -0.27
    /cs
    -0.26
    å¿ĥèĦıçĹħ
    -0.26
     alma
    -0.25
    POSITIVE LOGITS
    Pod
    0.32
     br
    0.31
    iding
    0.30
    radi
    0.30
    ate
    0.30
    æ¶Ī
    0.29
     Br
    0.28
    è¾IJå°Ħ
    0.28
    æķ£
    0.28
     Bl
    0.28
    Activations Density 0.000%

    No Known Activations