© 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. 9000
    Prev
    Next
    INDEX
    Explanations

    one

    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
    .pid
    -0.30
     mee
    -0.29
    ono
    -0.28
    icator
    -0.28
     Naked
    -0.27
    zo
    -0.26
     pid
    -0.25
    ä¸ī项
    -0.25
    egal
    -0.25
    isted
    -0.25
    POSITIVE LOGITS
    ardin
    0.26
    lotte
    0.25
     romant
    0.25
     foss
    0.25
    çĿ£ä¿ĥ
    0.24
    âĢ¢↵↵
    0.24
    ollen
    0.23
    éĥ¨åī¯
    0.23
    OLUM
    0.23
     SOUTH
    0.23
    Activations Density 0.101%

    No Known Activations