© 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. 33-TRANSCODER-HP
    7. 54211
    Prev
    Next
    INDEX
    Explanations

    enzymes and biological functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blade
    -0.28
     hÆ°á»Łng
    -0.28
     Catalyst
    -0.28
    åıįåºĶ
    -0.27
    umba
    -0.27
     Burning
    -0.25
    æĬĬæĪij
    -0.25
    ниÑĨа
    -0.25
     react
    -0.25
    exact
    -0.24
    POSITIVE LOGITS
    еж
    0.29
    åIJ¬è¯¾
    0.28
     ech
    0.28
    TRACK
    0.27
     mer
    0.27
     TRACK
    0.26
    å·¥ä¸ļä¼ģä¸ļ
    0.26
    èģĮèĥ½
    0.25
     st
    0.25
     scratch
    0.25
    Activations Density 0.158%

    No Known Activations