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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51802
    Prev
    Next
    INDEX
    Explanations

    hit-and-run

    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
    pur
    -0.09
    uka
    -0.09
    æķ¦
    -0.08
    cco
    -0.08
     br
    -0.08
    orz
    -0.08
    åĿŁ
    -0.08
    çł¥
    -0.08
    //{{
    -0.08
     Dam
    -0.08
    POSITIVE LOGITS
    gent
    0.10
    æĬ½
    0.09
    å°½
    0.09
    讲æķħäºĭ
    0.09
    tings
    0.09
     Plains
    0.09
    纶
    0.09
    teil
    0.09
    bits
    0.09
    orde
    0.09
    Activations Density 0.001%

    No Known Activations