© 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. 53628
    Prev
    Next
    INDEX
    Explanations

    and

    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
    éĽªèĬ±
    -0.26
     tit
    -0.26
    adt
    -0.25
     divers
    -0.25
    "title
    -0.25
    pez
    -0.24
    loo
    -0.24
     Ness
    -0.24
    .Enum
    -0.24
     Titles
    -0.24
    POSITIVE LOGITS
    æ¯Ķäºļ
    0.28
    hei
    0.27
    antro
    0.26
    imits
    0.26
    åŬ
    0.25
    æłĴ
    0.25
    åĴ¥
    0.25
    emics
    0.25
    æ¯ĶæĪij
    0.24
    æ¡Ħ
    0.24
    Activations Density 0.015%

    No Known Activations