© 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. 58397
    Prev
    Next
    INDEX
    Explanations

    impact influence

    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
    Negative Logits
    æĢı
    -0.28
     Mer
    -0.26
    ä¸įåģľ
    -0.26
    raq
    -0.26
    _Abstract
    -0.25
    _dummy
    -0.25
    lessly
    -0.24
    quent
    -0.24
    é»ijçĻ½
    -0.24
    ä¸įåģľåľ°
    -0.24
    POSITIVE LOGITS
     impact
    0.41
     influence
    0.36
    çļĦå½±åĵį
    0.35
    impact
    0.34
     role
    0.33
     impacts
    0.32
     effects
    0.32
     effect
    0.32
    å½±åĵį
    0.32
    å½±åĵįåĬĽ
    0.30
    Activations Density 0.004%

    No Known Activations