© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26347
    Prev
    Next
    INDEX
    Explanations

    of Mars

    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
    æµģåĩº
    -0.10
    æŁĺ
    -0.09
    亲çĪ±
    -0.09
    åıįè¿ĩæĿ¥
    -0.09
    ë²Ķ
    -0.09
    æ·ĺæ±°
    -0.08
    çĦĺ
    -0.08
    _Frame
    -0.08
    dob
    -0.08
    èµ
    -0.08
    POSITIVE LOGITS
    æģļ
    0.10
    éĴī
    0.09
    olean
    0.09
    åİķ
    0.09
    çĿ
    0.09
    篮
    0.09
    Luck
    0.08
    aba
    0.08
    大å§IJ
    0.08
    Lab
    0.08
    Activations Density 0.178%

    No Known Activations