© 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. 151292
    Prev
    Next
    INDEX
    Explanations

    different lengths

    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
    éłĨ
    -0.28
    нолог
    -0.28
    ç¦ģ
    -0.26
    åº
    -0.26
    å°ijãģªãģı
    -0.25
    身
    -0.25
    çİ°åľº
    -0.24
     Exclusive
    -0.24
    údo
    -0.24
    åħį
    -0.24
    POSITIVE LOGITS
     unequal
    0.52
    ä¸įä¸Ģæł·
    0.44
     uneven
    0.43
     Equal
    0.43
     equal
    0.42
    ä¸įåIJĮ
    0.42
     differing
    0.42
     differently
    0.40
    equal
    0.39
     different
    0.39
    Activations Density 0.948%

    No Known Activations