© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2127
    Prev
    Next
    INDEX
    Explanations

    original series or trilogy

    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
    åĮ»èį¯
    -0.23
    uant
    -0.23
    éĥ¨å§Ķ
    -0.23
    åĮ»çĶ¨
    -0.23
     Neural
    -0.23
     neighbor
    -0.23
     neural
    -0.22
    Ñĭва
    -0.22
     Æ°u
    -0.21
    -ng
    -0.21
    POSITIVE LOGITS
     trilogy
    0.31
    åIJİæľŁ
    0.30
    åİŁèijĹ
    0.29
    å¹ķåIJİ
    0.28
     series
    0.28
    ç»ıåħ¸
    0.28
     sequel
    0.26
     lore
    0.26
    ç³»åĪĹ
    0.26
    ç»ıåħ¸çļĦ
    0.26
    Activations Density 0.079%

    No Known Activations