© 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. 95073
    Prev
    Next
    INDEX
    Explanations

    art

    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
    nier
    -0.41
    åĽłæŀľ
    -0.29
     Det
    -0.27
    æŶæĬ¥
    -0.26
    èĥ¸
    -0.26
     Dere
    -0.25
    åĸĿéħĴ
    -0.25
    pisa
    -0.25
    ognito
    -0.24
     repercussions
    -0.24
    POSITIVE LOGITS
    work
    0.32
    FUL
    0.31
    ful
    0.31
    ule
    0.30
     art
    0.30
    Work
    0.30
    -work
    0.29
    _work
    0.29
    imate
    0.28
    Trait
    0.28
    Activations Density 0.007%

    No Known Activations