© 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. 23-TRANSCODER-HP
    7. 24040
    Prev
    Next
    INDEX
    Explanations

    Categories/Types/Grades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缮ãģ«
    -0.27
    èµĸ以
    -0.26
    ipc
    -0.26
    让æĤ¨
    -0.26
    ap
    -0.26
    .qq
    -0.25
    opc
    -0.24
    spath
    -0.24
    @section
    -0.24
     encounter
    -0.24
    POSITIVE LOGITS
    äge
    0.27
     VIA
    0.26
     Som
    0.24
    :frame
    0.24
     bada
    0.23
    .EN
    0.23
    edException
    0.23
    Ëī
    0.23
     sb
    0.23
    =center
    0.23
    Activations Density 0.065%

    No Known Activations