© 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. 23-TRANSCODER-HP
    7. 24056
    Prev
    Next
    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -divider
    -0.27
     Presidency
    -0.25
     tilt
    -0.24
    æĦı大
    -0.24
    rint
    -0.24
    ÑģÑĤÑĢ
    -0.24
     screenHeight
    -0.24
    oulder
    -0.24
    -fast
    -0.24
    scrollTop
    -0.24
    POSITIVE LOGITS
    æľ¬ç½ij
    0.28
     own
    0.28
    tered
    0.28
    èĩªå·±çļĦ
    0.28
     Own
    0.27
     notes
    0.27
     metadata
    0.26
     mnemonic
    0.25
     Zip
    0.25
    çĤ¹ç¼Ģ
    0.25
    Activations Density 0.089%

    No Known Activations