© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    classification, rating, code, organization

    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
     Atat
    -0.25
    oir
    -0.24
    rror
    -0.23
     Vân
    -0.22
    coll
    -0.22
    invalidate
    -0.22
    vard
    -0.21
    uring
    -0.21
    нима
    -0.21
    åı£æ°´
    -0.21
    POSITIVE LOGITS
    åĪĨç±»
    0.31
     Classification
    0.30
     classification
    0.29
    è±ģ
    0.28
     Catalog
    0.26
     categor
    0.25
    è¯Ħ为
    0.25
    è¯Ħ级
    0.25
     rating
    0.24
    è°ĥæŁ¥æĺ¾ç¤º
    0.24
    Activations Density 0.157%

    No Known Activations