© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36386
    Prev
    Next
    INDEX
    Explanations

    reports, agreements, correspondence

    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
     presently
    -0.09
    宣å¸ĥ
    -0.09
    åįłåľ°
    -0.09
    æ¹Ľ
    -0.09
    缮åīį
    -0.09
    宣åijĬ
    -0.09
    è¯Ĩ
    -0.08
    éĺµå®¹
    -0.08
    é¢Ī
    -0.08
     Canton
    -0.08
    POSITIVE LOGITS
    æĪijå½ĵæŶ
    0.12
    åı£å¾Ħ
    0.12
    å±¥èģĮ
    0.12
    é«ĺå±Ĥ
    0.11
    åĨ³çŃĸ
    0.11
    å½ĵæŶçļĦ
    0.11
    éĤ£ä¸ªæŶåĢĻ
    0.11
    å½ĵæŶ
    0.11
    é«ĺ管
    0.10
     должноÑģÑĤ
    0.10
    Activations Density 0.235%

    No Known Activations