© 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. 19-TRANSCODER-HP
    7. 8398
    Prev
    Next
    INDEX
    Explanations

    Names and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipse
    -0.25
    cura
    -0.24
    bp
    -0.24
     baja
    -0.23
     VO
    -0.23
    MO
    -0.23
    elles
    -0.23
    bor
    -0.23
    bel
    -0.23
    ium
    -0.22
    POSITIVE LOGITS
    -limit
    0.25
    æĹĮ
    0.24
    çĽ¸å·®
    0.22
    رÙĬØŃ
    0.22
    iske
    0.22
    强æľīåĬĽ
    0.22
     Bliss
    0.22
    :NS
    0.22
    è±¢
    0.21
    çĺ
    0.21
    Activations Density 0.055%

    No Known Activations