© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108537
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereafter
    -0.30
    aho
    -0.27
     amounted
    -0.27
    æĶ¾åľ¨
    -0.27
    æĢ¥
    -0.25
    åľ¨äºİ
    -0.25
     sounded
    -0.25
    ä½ĵçİ°åľ¨
    -0.25
    ÑĭваеÑĤÑģÑı
    -0.24
     entails
    -0.24
    POSITIVE LOGITS
    ber
    0.28
    _PRESENT
    0.26
    å¨ĺ
    0.25
    thing
    0.25
    ghi
    0.25
     kost
    0.25
    å¼ĵ
    0.24
     bumps
    0.24
     tph
    0.23
    quals
    0.23
    Activations Density 0.982%

    No Known Activations