© 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. 53238
    Prev
    Next
    INDEX
    Explanations

    bullet and projectile

    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
    forth
    -0.11
    ä¸Ģ天
    -0.09
    åŁĴ
    -0.09
    髦
    -0.09
    äºĭåIJİ
    -0.09
    ilton
    -0.09
    ideon
    -0.09
    å¯¹ä½ł
    -0.09
    ä¸Ģå¤ľ
    -0.09
    adays
    -0.08
    POSITIVE LOGITS
    ÑģÑĤой
    0.09
    æľŁæĿĥ
    0.09
    mans
    0.09
    ivia
    0.09
    ì±ħ
    0.08
    AppState
    0.08
    æĢ»éĺŁ
    0.08
    ting
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    ucid
    0.08
    Activations Density 0.009%

    No Known Activations