© 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. 39261
    Prev
    Next
    INDEX
    Explanations

    generate / generating

    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
    аÐ
    -0.11
    ово
    -0.10
    äºĭæķħåıijçĶŁ
    -0.09
    å¥
    -0.09
    çķĽ
    -0.09
    _atts
    -0.09
    STRU
    -0.09
    .FETCH
    -0.09
    å°Ŀ
    -0.09
    glich
    -0.08
    POSITIVE LOGITS
    çģ«èĬ±
    0.11
    çĥŃæ½®
    0.10
     generated
    0.10
     generate
    0.10
    .generate
    0.09
    åºŁå¼ĥçī©
    0.09
    enerate
    0.09
    èĩªè±ª
    0.09
     Generate
    0.09
     generating
    0.09
    Activations Density 0.102%

    No Known Activations