© 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. 51271
    Prev
    Next
    INDEX
    Explanations

    length or long dimensions

    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
    å·²ä¹ħçļĦ
    -0.08
    çĸij
    -0.08
    lip
    -0.08
    鼶è·Ŀ离
    -0.08
    åħĪè¡Į
    -0.08
    æ»ĥ
    -0.08
    oldt
    -0.07
    quila
    -0.07
    çĬ¹è±«
    -0.07
    æĿł
    -0.07
    POSITIVE LOGITS
    åı¯è¾¾
    0.11
    çĴĭ
    0.10
    å§Ŀ
    0.09
    unta
    0.09
    çĹ´
    0.09
    å¹´æĬ¥
    0.09
    æĺ¯æľī
    0.09
    ëĥ¥
    0.09
    身åŃIJ
    0.09
    :length
    0.09
    Activations Density 0.087%

    No Known Activations