© 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. 95475
    Prev
    Next
    INDEX
    Explanations

    Place names

    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
    è¿ĩ
    -0.34
    hus
    -0.29
     over
    -0.27
     Slam
    -0.27
     hatch
    -0.27
    祧
    -0.26
    over
    -0.25
     cross
    -0.25
     pet
    -0.25
    ä¸Ńä»ĭ
    -0.25
    POSITIVE LOGITS
    Filed
    0.33
    è¢ħ
    0.29
    éĵij
    0.27
    erne
    0.27
    기ìĹIJ
    0.26
     gridSize
    0.25
     Yap
    0.25
    mars
    0.25
     stars
    0.25
    -stars
    0.25
    Activations Density 0.092%

    No Known Activations