© 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. 27-TRANSCODER-HP
    7. 7987
    Prev
    Next
    INDEX
    Explanations

    Trans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è·ĥ
    -0.26
    èģĶç³»æĸ¹å¼ı
    -0.26
    è®´
    -0.25
    é£ŀè·ĥ
    -0.25
    èºį
    -0.24
    è¿İ
    -0.24
     antenn
    -0.24
    æijģ
    -0.24
    uC
    -0.24
    dB
    -0.24
    POSITIVE LOGITS
     reap
    0.29
    corp
    0.28
     rub
    0.28
     rein
    0.27
    embre
    0.26
    acad
    0.26
    arith
    0.26
    auty
    0.25
     Verse
    0.25
    croft
    0.25
    Activations Density 0.012%

    No Known Activations