© 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. 52714
    Prev
    Next
    INDEX
    Explanations

    finding things

    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
    .sam
    -0.10
    EDGE
    -0.09
    è§Ī
    -0.09
    åĩĨç¡®
    -0.09
    earer
    -0.09
    edge
    -0.09
    è¶ĭåIJij
    -0.09
    èĬ³é¦Ļ
    -0.08
    éĢ£çºĮ
    -0.08
    .Brand
    -0.08
    POSITIVE LOGITS
    æį¡
    0.14
    äºĮæīĭ
    0.13
    æĭ¾
    0.12
     acquisition
    0.12
    æĬ¢æķij
    0.11
    æ·ĺå®Ŀ
    0.11
    èĥ½æī¾åĪ°
    0.11
     eBay
    0.11
    æĶ¶è´Ń
    0.11
    å»īä»·
    0.11
    Activations Density 0.089%

    No Known Activations