© 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. 24-TRANSCODER-HP
    7. 150554
    Prev
    Next
    INDEX
    Explanations

    Anton

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trafficking
    -0.39
    è´©åįĸ
    -0.31
    ourcing
    -0.31
    è´§æºIJ
    -0.31
     venta
    -0.30
     Traff
    -0.30
    å¸ĤåľºéľĢæ±Ĥ
    -0.30
     comerc
    -0.30
     illegal
    -0.29
    å¸Ĥåľºä¸Ĭ
    -0.29
    POSITIVE LOGITS
    é©»
    0.31
    azor
    0.27
    æµĭéĩı
    0.27
    ัà¸Ķ
    0.25
     vis
    0.25
    çģ«å±±
    0.25
    fat
    0.25
     nou
    0.24
     fat
    0.24
    -fat
    0.24
    Activations Density 0.909%

    No Known Activations