© 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. 151237
    Prev
    Next
    INDEX
    Explanations

    is/are

    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
    åĹľ
    -0.32
    nesia
    -0.28
     whisper
    -0.27
    enaries
    -0.26
    æĺ¯ä¸Ģ座
    -0.26
    .Assertions
    -0.25
    ACHI
    -0.25
    .dex
    -0.25
    ä¹Ĵ
    -0.25
    iveness
    -0.24
    POSITIVE LOGITS
     available
    0.41
     Available
    0.36
    available
    0.33
    Available
    0.32
     disponible
    0.30
     dispon
    0.29
    -available
    0.28
     included
    0.28
     grate
    0.27
     free
    0.26
    Activations Density 0.242%

    No Known Activations