© 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. 58296
    Prev
    Next
    INDEX
    Explanations

    Sums

    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
    ancode
    -0.26
     kê
    -0.25
     flash
    -0.25
    è£ħå¤ĩ
    -0.24
     ret
    -0.24
    Mic
    -0.24
    yst
    -0.24
     métier
    -0.24
    asa
    -0.24
    _flash
    -0.24
    POSITIVE LOGITS
     summ
    1.10
    summ
    0.93
     sum
    0.91
     sums
    0.87
    sum
    0.85
    Sum
    0.84
     Sum
    0.80
     summed
    0.78
    _sum
    0.76
    âĪij
    0.76
    Activations Density 0.014%

    No Known Activations