© 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. 8039
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
    amenti
    -0.27
    atk
    -0.26
    uo
    -0.24
    æİĺ
    -0.24
    æľ¬äºº
    -0.24
    uliar
    -0.24
    rax
    -0.23
    onomous
    -0.23
    nox
    -0.23
     rés
    -0.23
    POSITIVE LOGITS
    åı¯ä»¥èİ·å¾Ĺ
    0.27
    ä½ĵåĪ¶æĶ¹éĿ©
    0.27
     undecided
    0.26
    çŃ
    0.25
     uninterrupted
    0.25
    Rew
    0.25
    åºĶæĢ¥é¢Ħæ¡Ī
    0.25
    ä¼ģä¸ļæıIJä¾Ľ
    0.24
    (alpha
    0.24
     Rewrite
    0.24
    Activations Density 0.002%

    No Known Activations