© 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. 24036
    Prev
    Next
    INDEX
    Explanations

    siren, maid, nymph, sudo, span

    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
    å¹ħ
    -0.10
    ë²
    -0.09
    饥饿
    -0.09
    kdir
    -0.09
    ¨
    -0.09
    ä¸Ģå®ļçļĦ
    -0.08
    sembler
    -0.08
    è§ĩ
    -0.08
    çķĻå®Ī
    -0.08
    é«ĺåİŁ
    -0.08
    POSITIVE LOGITS
    æ¶Īè´¹åįĩ级
    0.10
    è¢ħ
    0.09
    oran
    0.09
    座è°Īä¼ļä¸Ĭ
    0.09
     знаÑĤÑĮ
    0.09
    å¤ĦåĪĨ
    0.09
    鸥
    0.09
    bole
    0.09
    ooth
    0.09
    ç¬Ĩ
    0.09
    Activations Density 0.006%

    No Known Activations