© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3368
    Prev
    Next
    INDEX
    Explanations

    tax shelter, tax-exempt, tax return, tax incentives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    NESS
    -0.21
    hood
    -0.20
    chaft
    -0.19
    à´Ł
    -0.18
    keit
    -0.18
    å¤ļç§įå½¢å¼ı
    -0.18
    èĥ¸åı£
    -0.18
    erval
    -0.18
    halt
    -0.18
    медиÑĨинÑģк
    -0.17
    POSITIVE LOGITS
    onomies
    0.33
    onom
    0.31
    worthy
    0.30
    onomic
    0.29
    payer
    0.25
    plorer
    0.23
    able
    0.23
    lify
    0.22
    onomy
    0.22
    -conscious
    0.21
    Activations Density 0.026%

    No Known Activations