© 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. 97038
    Prev
    Next
    INDEX
    Explanations

    cells

    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
    Negative Logits
     gains
    -0.34
     gain
    -0.33
     gaining
    -0.32
     parts
    -0.30
    _gain
    -0.28
    gain
    -0.28
    -parts
    -0.27
    å¾ĹåĪ°
    -0.27
    Gain
    -0.27
     gained
    -0.26
    POSITIVE LOGITS
    åĪĨåĮĸ
    0.31
    åħ·æľī
    0.30
     differentiation
    0.28
     differentiate
    0.28
    ouro
    0.28
    å·®å¼ĤåĮĸ
    0.28
     possesses
    0.27
     found
    0.27
     flotation
    0.26
     yat
    0.26
    Activations Density 0.004%

    No Known Activations