© 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. 151347
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    表示
    -0.30
     offending
    -0.28
    并ä¸į代表
    -0.28
    аÑĨиÑİ
    -0.25
    ä»ŀ
    -0.25
    鼷æĸ¯
    -0.25
    ëĨĵ
    -0.25
     Wizard
    -0.24
    ä½Ĩä»İ
    -0.24
    åľ°è¯´
    -0.24
    POSITIVE LOGITS
    以便
    0.29
     fused
    0.28
    _lens
    0.28
    elas
    0.26
    datal
    0.26
    ĪæĿĥ
    0.26
     helicopt
    0.25
    ilar
    0.24
    èij±
    0.24
     soaked
    0.23
    Activations Density 0.907%

    No Known Activations