© 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. 88179
    Prev
    Next
    INDEX
    Explanations

    s

    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
    panse
    -0.25
    eras
    -0.25
     blush
    -0.25
    è¸Į
    -0.24
    race
    -0.24
     clen
    -0.23
    ç«ĭéĿ¢
    -0.23
    åĨĴçĿĢ
    -0.23
    lit
    -0.23
     rooting
    -0.23
    POSITIVE LOGITS
    Sol
    0.31
    çĭ¬æľīçļĦ
    0.29
     optional
    0.28
     thing
    0.28
    çļĦä¸Ģ项
    0.28
     Sol
    0.27
     arisen
    0.27
     hallmark
    0.27
     intrinsic
    0.26
    quired
    0.25
    Activations Density 0.006%

    No Known Activations