© 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. 10883
    Prev
    Next
    INDEX
    Explanations

    looking forward to

    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
    REE
    -0.09
    .iv
    -0.09
    èģĶ
    -0.09
    ucing
    -0.09
    ucs
    -0.08
    è¾£
    -0.08
    uche
    -0.08
     CHR
    -0.08
    SCAN
    -0.08
    é»ĺé»ĺåľ°
    -0.08
    POSITIVE LOGITS
    欢è¿İ大家
    0.11
    æ¸ħåĩī
    0.10
    大家
    0.09
     sob
    0.09
    иÑĤа
    0.09
    ä¼Ĺ
    0.09
    éĤ£éĩĮ
    0.09
     attendance
    0.08
    .spy
    0.08
    çļĦ身影
    0.08
    Activations Density 0.007%

    No Known Activations