© 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. 22-TRANSCODER-HP
    7. 98289
    Prev
    Next
    INDEX
    Explanations

    smooth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnore
    -0.25
    automation
    -0.23
     coli
    -0.23
    ãģ¨ãģĦãģ£ãģ¦
    -0.23
    hints
    -0.23
    avr
    -0.22
    elson
    -0.22
    媽
    -0.22
    -sdk
    -0.21
    ãģ«ãĤĤ
    -0.21
    POSITIVE LOGITS
     enough
    0.34
    ness
    0.30
    ingly
    0.29
    board
    0.27
     transition
    0.26
    ë¡Ń
    0.26
    licity
    0.25
    itude
    0.25
    çIJĨäºĭä¼ļ
    0.25
    s
    0.24
    Activations Density 0.212%

    No Known Activations