© 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. 9614
    Prev
    Next
    INDEX
    Explanations

    Early

    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
    orate
    -0.31
    足以
    -0.27
    å¹´åºķ
    -0.27
    尺度
    -0.26
    秾
    -0.26
    æĵį
    -0.25
    å½±éŁ³
    -0.25
    -hide
    -0.25
    ("'"
    -0.25
     begr
    -0.24
    POSITIVE LOGITS
     experiments
    0.29
     estimates
    0.28
     on
    0.28
    <dd
    0.28
     upon
    0.28
     for
    0.27
     suspension
    0.26
    experiment
    0.26
    派驻
    0.26
     evidence
    0.26
    Activations Density 0.006%

    No Known Activations