© 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. 24-TRANSCODER-HP
    7. 149377
    Prev
    Next
    INDEX
    Explanations

    "ow" or "Ow" names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    (direction
    -0.27
    ponsive
    -0.26
    åı¯èĥ½åıijçĶŁ
    -0.25
    æĸ¹åIJij
    -0.25
    æĿŁ
    -0.25
    (!_
    -0.24
    asca
    -0.24
    åıijå±ķ空éĹ´
    -0.23
    endance
    -0.23
    nee
    -0.23
    POSITIVE LOGITS
    乡
    0.26
    sg
    0.25
    uos
    0.25
    æīij
    0.25
    ä¾Ĩ
    0.24
    éĦī
    0.24
     Unary
    0.24
    ÑģÑĤвеннÑĭе
    0.24
    ourse
    0.24
    Slf
    0.24
    Activations Density 1.891%

    No Known Activations