© 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. 51705
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
    ä¸įä¸ĭ
    -0.10
    à¹Ĥà¸ģ
    -0.10
    åłµ
    -0.09
    å¢ī
    -0.08
    ám
    -0.08
    临
    -0.08
    IVO
    -0.08
     конкÑĥÑĢÑģ
    -0.08
    è¿IJæ²³
    -0.08
    çķª
    -0.08
    POSITIVE LOGITS
    æŁĶ
    0.10
    è¾°
    0.10
    人å±ħ
    0.10
    éĶij
    0.10
    ä¸īå±Ĥ
    0.09
    OptionsResolver
    0.09
    psc
    0.09
    .Xr
    0.09
    ihn
    0.09
    æµĶ
    0.09
    Activations Density 0.006%

    No Known Activations