© 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. 108389
    Prev
    Next
    INDEX
    Explanations

    wed

    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
    isz
    -0.26
     CONTRIBUTORS
    -0.25
    arf
    -0.25
    å¿ĺ
    -0.24
    neg
    -0.24
     tú
    -0.24
    sorted
    -0.23
    ä¸ļ绩
    -0.23
    çĬ¹
    -0.23
    esti
    -0.23
    POSITIVE LOGITS
    ez
    0.27
    GRAM
    0.26
    utow
    0.26
    /moment
    0.25
    Pager
    0.25
    ãĤŃãĥ³ãĤ°
    0.24
    ober
    0.24
    éģ¥æݧ
    0.24
    ulers
    0.24
    EW
    0.24
    Activations Density 0.700%

    No Known Activations