© 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. 24646
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     dang
    -0.29
    ḣ
    -0.25
    -gap
    -0.25
    etting
    -0.24
     tunes
    -0.24
    rew
    -0.24
    utory
    -0.24
    åģı好
    -0.23
    éĹ¯
    -0.23
    (s
    -0.23
    POSITIVE LOGITS
    空æ°Ķä¸Ń
    0.29
    icina
    0.25
     Lad
    0.24
    çķĮ第ä¸Ģ
    0.24
    ework
    0.24
    _REPEAT
    0.24
    çīĪæĿĥ声æĺİ
    0.24
    _locale
    0.24
    è¿Ļä¸Ģå¹´
    0.24
    æıIJä¾ĽçļĦ
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.