© 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. 150238
    Prev
    Next
    INDEX
    Explanations

    Names, dates, identifiers

    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
    nect
    -0.29
    istance
    -0.29
    hsi
    -0.27
     prive
    -0.27
    .getOwnProperty
    -0.27
    åİħ
    -0.26
    æŃ£æĺ¯åĽłä¸º
    -0.25
    iro
    -0.25
    .Must
    -0.25
    iele
    -0.24
    POSITIVE LOGITS
    åħ¼
    0.28
    venture
    0.26
    uments
    0.24
    oad
    0.24
    Legend
    0.24
    çĴľ
    0.24
    ued
    0.24
    ÑĨов
    0.23
    ytt
    0.23
    èħº
    0.23
    Activations Density 0.117%

    No Known Activations