© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    catch phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    etten
    -0.19
    ethod
    -0.18
    PHA
    -0.18
    ondon
    -0.18
     turf
    -0.18
    对å¾ħ
    -0.18
    ATIC
    -0.18
    crest
    -0.18
    getTable
    -0.17
    ftware
    -0.17
    POSITIVE LOGITS
    -all
    0.27
     glimpse
    0.25
    æĹ¶æľº
    0.23
    point
    0.23
    ãĤĤãģ®
    0.21
    书记
    0.20
    fall
    0.20
    phrase
    0.20
    ÙĨÙĬ
    0.20
    ling
    0.20
    Activations Density 0.026%

    No Known Activations