© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    allow access for

    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
     ÙħدÙī
    -0.11
    å¯ĤéĿĻ
    -0.10
    æ²ĥå°Ķ
    -0.10
    以åıĬåħ¶ä»ĸ
    -0.09
    oola
    -0.09
    æĪij们çİ°åľ¨
    -0.09
    é»ĺé»ĺåľ°
    -0.09
     оÑĤкÑĢÑĭва
    -0.09
    该游æĪı
    -0.09
    ango
    -0.09
    POSITIVE LOGITS
     greater
    0.08
    8
    0.08
    åĥļ
    0.08
    9
    0.08
    _cmds
    0.08
    æѧ
    0.08
    tim
    0.07
    aise
    0.07
    ason
    0.07
    5
    0.07
    Activations Density 0.045%

    No Known Activations