© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    both...and

    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
    lect
    -0.09
    7
    -0.08
    ä¸Ģæł·
    -0.08
     laps
    -0.08
    jie
    -0.08
    ä¸Ģ樣
    -0.08
    9
    -0.08
    5
    -0.08
    鼷
    -0.08
    urb
    -0.08
    POSITIVE LOGITS
    ORN
    0.11
    schütz
    0.10
    è²Ĭ
    0.09
     pomi
    0.09
    åĭī
    0.09
    åľ¨å½ĵåľ°
    0.09
     McCabe
    0.09
    errat
    0.09
    ç¦
    0.09
    åıijçİ°éĹ®é¢ĺ
    0.09
    Activations Density 0.048%

    No Known Activations