© 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. 53843
    Prev
    Next
    INDEX
    Explanations

    company names and/or copyright

    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
    æĮ¯
    -0.27
     reloading
    -0.26
    opaque
    -0.26
    UUID
    -0.25
    失败
    -0.25
     Trib
    -0.24
    separator
    -0.24
    è§ī
    -0.24
    失
    -0.24
    é²ľæĺİ
    -0.24
    POSITIVE LOGITS
    itat
    0.32
    çªĪ
    0.30
    wand
    0.28
     financial
    0.27
     Financial
    0.26
    ya
    0.26
    è´¢
    0.26
     dors
    0.25
    anders
    0.25
    jang
    0.25
    Activations Density 0.002%

    No Known Activations