© 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. 3335
    Prev
    Next
    INDEX
    Explanations

    Al with following syllables

    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
    人人éĥ½
    -0.21
    ëģĶ
    -0.21
    ll
    -0.19
    epy
    -0.19
    szed
    -0.18
    hợ
    -0.18
     Ukr
    -0.18
    gli
    -0.18
    STANCE
    -0.18
    OrNil
    -0.18
    POSITIVE LOGITS
    ways
    0.30
    oney
    0.26
    istically
    0.26
    dehyde
    0.25
    thus
    0.24
    istic
    0.24
    buquerque
    0.23
    uminum
    0.23
    gebra
    0.23
    ston
    0.22
    Activations Density 0.063%

    No Known Activations