© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10715
    Prev
    Next
    INDEX
    Explanations

    Django, William Walker, Plains, outlaw, cowboy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    黾
    -0.09
     Swim
    -0.09
    大åıij
    -0.09
    é¼ĭ
    -0.08
    çIJĨ工大åѦ
    -0.08
    天é¹ħ
    -0.08
    游泳
    -0.08
    ì§ij
    -0.08
    ICA
    -0.08
     phÆ°á»Ŀng
    -0.08
    POSITIVE LOGITS
    éķĸ
    0.13
     cowboy
    0.11
    èįīåİŁ
    0.11
    åĨľæľº
    0.11
    çīĽ
    0.11
    çī§åľº
    0.10
    屯
    0.10
     outlaw
    0.10
     Wyoming
    0.10
    åĨľå®¶
    0.10
    Activations Density 0.163%

    No Known Activations