© 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. 30-TRANSCODER-HP
    7. 95800
    Prev
    Next
    INDEX
    Explanations

    medical topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     INTERN
    -0.26
    ajes
    -0.26
     Má»įi
    -0.25
    ä¸ĸçķĮè§Ĥ
    -0.25
    erb
    -0.25
     neutrality
    -0.24
    èµ·
    -0.24
     Neb
    -0.24
    marks
    -0.24
    æŃ¥æŃ¥
    -0.24
    POSITIVE LOGITS
    èĥ±
    0.31
     fragile
    0.28
     crystal
    0.26
    edar
    0.26
     pur
    0.26
    solid
    0.26
     rep
    0.26
     solid
    0.26
    uto
    0.26
    hair
    0.26
    Activations Density 0.883%

    No Known Activations