© 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. 49165
    Prev
    Next
    INDEX
    Explanations

    all time, history, recent times

    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
    åħħåĪĨä½ĵçİ°
    -0.09
    ä¹Ķ
    -0.09
    è¡£
    -0.09
    è¿Ļæīį
    -0.09
    ĵĺ
    -0.09
    æĺİå¹´
    -0.09
    ä¸ºæľŁ
    -0.08
    衾
    -0.08
    iant
    -0.08
    .lift
    -0.08
    POSITIVE LOGITS
    年代
    0.11
    年以æĿ¥
    0.11
    åŃº
    0.11
    以æĿ¥
    0.10
    å¹´æĿ¥
    0.10
    agal
    0.10
    æĺĶ
    0.10
    past
    0.10
    ä¹ħ
    0.10
    åı¼
    0.10
    Activations Density 0.066%

    No Known Activations