© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2874
    Prev
    Next
    INDEX
    Explanations

    launched, wool, linkage, apid

    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
    æ¹ĸåĮº
    -0.09
    æµĩ
    -0.09
    ocal
    -0.08
    à¹Ĥà¸Ļ
    -0.08
    ìķ
    -0.08
    çģĮæºī
    -0.08
     tog
    -0.08
     quadr
    -0.08
    _lift
    -0.08
     feed
    -0.08
    POSITIVE LOGITS
    åļ¼
    0.12
    å®ĹæŨ
    0.10
    stry
    0.10
    axon
    0.09
    æ¯ĶæĪij
    0.09
    éĺµéĺµ
    0.09
    帼
    0.09
    èĴº
    0.09
    çĹĺ
    0.09
    å¸ĺ
    0.09
    Activations Density 0.122%

    No Known Activations