© 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. 7984
    Prev
    Next
    INDEX
    Explanations

    2

    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
     refl
    -0.27
     ref
    -0.26
     ifndef
    -0.26
    ä¸ĩ个
    -0.26
    (ref
    -0.25
    æĽ´å¤ļçļĦ
    -0.25
    åIJĪéĢĤçļĦ
    -0.25
    -Identifier
    -0.24
    änge
    -0.24
    å°±è¡ĮäºĨ
    -0.24
    POSITIVE LOGITS
    eder
    0.26
     fr
    0.25
    mvc
    0.25
    åIJĦåįķä½į
    0.25
    FINE
    0.25
    heimer
    0.24
     AIM
    0.24
    ozilla
    0.24
    aeda
    0.24
    .perm
    0.23
    Activations Density 0.007%

    No Known Activations