© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10405
    Prev
    Next
    INDEX
    Explanations

    Warheads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ç¿»
    -0.23
    dy
    -0.22
    azz
    -0.21
    orsk
    -0.21
     Vern
    -0.20
     weekday
    -0.19
    abo
    -0.19
    褪
    -0.19
    kin
    -0.19
    mel
    -0.19
    POSITIVE LOGITS
    atum
    0.20
    à¸Ħะà¹ģà¸Ļ
    0.18
    踱
    0.18
    _continue
    0.17
    inati
    0.17
     DOI
    0.17
    ￦
    0.17
     Coverage
    0.17
    iske
    0.17
    avery
    0.17
    Activations Density 0.003%

    No Known Activations