© 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. 42325
    Prev
    Next
    INDEX
    Explanations

    adjuvant medical treatments/additives

    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
     Chim
    -0.29
     Courier
    -0.27
     chim
    -0.27
     chimney
    -0.27
    ä¸įä¸ĭ
    -0.25
     Ñģез
    -0.25
    arto
    -0.25
    åı¯èĥ½åĩºçİ°
    -0.25
    è¿IJè¡Į
    -0.24
    è¾Ľ
    -0.24
    POSITIVE LOGITS
    velle
    0.27
    å°ıå°ı
    0.26
     Scot
    0.26
    avo
    0.26
     lÆ°u
    0.25
    åºŁ
    0.24
    æıĦ
    0.24
    .apps
    0.23
     Bedford
    0.23
    VES
    0.23
    Activations Density 0.002%

    No Known Activations