© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7104
    Prev
    Next
    INDEX
    Explanations

    variety

    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
    ogne
    -0.31
    elder
    -0.30
    squ
    -0.29
    ildo
    -0.28
    åŀĭä¼ģä¸ļ
    -0.27
    éĻIJãĤĬ
    -0.26
    äºĭ實
    -0.26
    æī¾ä¸įåĪ°
    -0.25
    .magnitude
    -0.24
    ampoo
    -0.24
    POSITIVE LOGITS
    mb
    0.28
    \Helpers
    0.28
    atal
    0.27
    C
    0.26
    æıIJåīį
    0.26
    çªľ
    0.25
    æķ¢
    0.25
    ivism
    0.25
    ivist
    0.24
    åīª
    0.24
    Activations Density 0.005%

    No Known Activations