© 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. 25153
    Prev
    Next
    INDEX
    Explanations

    clean

    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
    æĺ¾
    -0.31
    aper
    -0.26
    pered
    -0.26
    iveness
    -0.25
    girls
    -0.24
    tile
    -0.24
    rophic
    -0.24
     qx
    -0.24
    -added
    -0.23
     apparent
    -0.23
    POSITIVE LOGITS
    çł¥
    0.28
    ighth
    0.26
    ensa
    0.25
    ening
    0.25
    $action
    0.25
     sesame
    0.24
    ç¼Ĺ
    0.24
    èŀ³
    0.24
    NING
    0.24
    andes
    0.24
    Activations Density 0.063%

    No Known Activations