© 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. 55500
    Prev
    Next
    INDEX
    Explanations

    mapping APIs and databases

    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
    æīĵæī«
    -0.09
    audi
    -0.08
    juan
    -0.08
    ä»İ严
    -0.08
    ibox
    -0.08
    æį®æĬ¥éģĵ
    -0.08
    æ±°
    -0.08
    éª
    -0.08
    aul
    -0.08
    amax
    -0.08
    POSITIVE LOGITS
    çļĦåľ°åĽ¾
    0.14
    åľ°åĽ¾
    0.13
    åľ°çIJĨ
    0.12
    驾车
    0.11
     ge
    0.11
    åį«æĺŁ
    0.10
    çļĦåŁİå¸Ĥ
    0.10
    åľ°è²Į
    0.10
    èĪªç©º
    0.10
    æµĭç»ĺ
    0.10
    Activations Density 0.428%

    No Known Activations