© 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. 30-TRANSCODER-HP
    7. 96605
    Prev
    Next
    INDEX
    Explanations

    dental

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿIJ
    -0.31
    ster
    -0.28
    unken
    -0.27
    æŃ»åĪij
    -0.25
    ä½ľçĶ¨
    -0.25
    imonial
    -0.25
     Ster
    -0.24
    instein
    -0.24
     pinch
    -0.24
    åĬŀ
    -0.24
    POSITIVE LOGITS
    ạn
    0.30
    leck
    0.28
    programming
    0.27
    åĬ©
    0.27
    æ½¼
    0.27
    alu
    0.26
    andan
    0.26
    磫æŃ£
    0.26
    çīĮçħ§
    0.26
    oller
    0.26
    Activations Density 0.011%

    No Known Activations