© 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. 30-TRANSCODER-HP
    7. 95284
    Prev
    Next
    INDEX
    Explanations

    Er

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dis
    -0.64
     neutral
    -0.57
    åĪĨ解
    -0.54
    neutral
    -0.53
     Neutral
    -0.52
    .dis
    -0.51
     disconnect
    -0.50
     disruption
    -0.49
     Dis
    -0.48
    dis
    -0.48
    POSITIVE LOGITS
    åĬŀ
    0.32
     cleans
    0.31
     Cleans
    0.30
    ERIC
    0.30
    æ¸ħæ´Ĺ
    0.29
    æĵ¦
    0.29
    Er
    0.28
    _ER
    0.28
    æ´Ĺ
    0.28
    eria
    0.26
    Activations Density 0.906%

    No Known Activations