© 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. 37658
    Prev
    Next
    INDEX
    Explanations

    suffice to say / short version

    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
    éĩįè§Ĩ
    -0.10
     Hag
    -0.09
    æĦıä¹ī
    -0.08
    çľĭæ¸ħ
    -0.08
    ÑĮÑİ
    -0.08
    veis
    -0.08
    èĮ«
    -0.08
    orous
    -0.08
     fila
    -0.08
    _CONTROL
    -0.08
    POSITIVE LOGITS
    è½®
    0.11
    annon
    0.10
     пока
    0.09
    åıªèĥ½è¯´
    0.09
    eldon
    0.09
    fone
    0.09
    rent
    0.09
    å®
    0.08
    lopedia
    0.08
    ä¸į便
    0.08
    Activations Density 0.006%

    No Known Activations