© 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. 149293
    Prev
    Next
    INDEX
    Explanations

    Fourier

    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
    erry
    -0.30
    ery
    -0.28
    ERY
    -0.27
    erland
    -0.26
    ec
    -0.24
    è¾ŀ
    -0.24
    ouple
    -0.24
    è¾Ń
    -0.24
    ERRY
    -0.24
    asters
    -0.24
    POSITIVE LOGITS
     è¾ĵ
    0.29
    ç»ĵæĻ¶
    0.26
    è¾ĵ
    0.26
     quần
    0.25
    åĪ°ä½į
    0.25
    ren
    0.25
    _keeper
    0.25
    igue
    0.25
     ACM
    0.24
     sym
    0.24
    Activations Density 0.228%

    No Known Activations