© 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. 130167
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    @g
    -0.27
     ÐľÐ¾
    -0.26
     Tonight
    -0.26
    cen
    -0.26
     MX
    -0.26
    Motion
    -0.25
    æľĢ强
    -0.25
    :variables
    -0.25
    .scala
    -0.25
    å¹´èĸª
    -0.25
    POSITIVE LOGITS
    ovie
    0.30
     present
    0.27
    对ç«ĭ
    0.27
    æµ·
    0.27
    ä¿ĿéĻ©åħ¬åı¸
    0.26
    ä¿ĿéĻ©
    0.26
     insured
    0.25
    害æĢķ
    0.25
    çĹĩ
    0.25
     because
    0.25
    Activations Density 0.004%

    No Known Activations