© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25499
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    Negative Logits
    ":
    -0.28
    表çݰ为
    -0.28
    :
    -0.27
    åIJĦè¡ĮåIJĦ
    -0.26
    umpt
    -0.25
    BindingUtil
    -0.25
    è¾Ĭ
    -0.25
    ':
    -0.25
    rowave
    -0.25
    ewart
    -0.25
    POSITIVE LOGITS
    xbc
    0.30
    eldom
    0.28
    SN
    0.27
    éĤ£ä¸Ģ
    0.27
    toFloat
    0.27
    éĥ½æ²¡æľī
    0.27
    并没æľī
    0.26
    寥
    0.25
    æĦıè§ģåıįé¦Ī
    0.25
    å®ŀåľ¨å¤ª
    0.24
    Activations Density 0.004%

    No Known Activations