© 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. 43314
    Prev
    Next
    INDEX
    Explanations

    medical/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
    äd
    -0.27
    iteDatabase
    -0.26
    ä¸ĵ线
    -0.26
    éļį
    -0.25
    è¿©
    -0.24
    OperationException
    -0.24
    大åħ¨
    -0.24
    iese
    -0.24
    Got
    -0.24
    被æĬĵ
    -0.24
    POSITIVE LOGITS
    bt
    0.29
    æĭĦ
    0.27
    br
    0.27
    bp
    0.27
    æħ¢
    0.25
    mc
    0.25
    zp
    0.25
    çľ¼çľĭ
    0.25
    zt
    0.25
    æį
    0.25
    Activations Density 0.002%

    No Known Activations