© 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. 25-TRANSCODER-HP
    7. 107570
    Prev
    Next
    INDEX
    Explanations

    frac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emas
    -0.26
    éĢ£çºĮ
    -0.25
    empre
    -0.25
    velt
    -0.25
    dbus
    -0.24
    atypes
    -0.24
    Configs
    -0.24
    ija
    -0.23
    ctor
    -0.23
    åħ¬ç§¯
    -0.23
    POSITIVE LOGITS
    ç©¿
    0.29
    æİĴ
    0.27
    orget
    0.27
     Kore
    0.26
    AIR
    0.26
    omm
    0.25
    urette
    0.25
    è´¯
    0.25
     compile
    0.24
    heed
    0.23
    Activations Density 0.933%

    No Known Activations