© 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. 24699
    Prev
    Next
    INDEX
    Explanations

    pregnancy

    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
    éĤ£åıª
    -0.25
    æ¯ħ
    -0.25
    éĤ£ä½į
    -0.25
    åºĵéĩĮ
    -0.24
    omon
    -0.24
    MenuItem
    -0.24
    空æ°Ķä¸Ń
    -0.24
    ture
    -0.23
    ç»ıåħ¸çļĦ
    -0.23
    iquid
    -0.23
    POSITIVE LOGITS
    IOR
    0.27
    ufe
    0.25
    elt
    0.24
    integration
    0.23
     stats
    0.23
    å©Ĭ
    0.23
    <Transform
    0.23
    eca
    0.23
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.23
     sided
    0.22
    Activations Density 0.010%

    No Known Activations