© 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. 5466
    Prev
    Next
    INDEX
    Explanations

    the same

    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
    ìķħ
    -0.10
    åŀĤ
    -0.09
    æľĢåĪĿ
    -0.09
    å³°åĢ¼
    -0.09
    åı®
    -0.09
    åĪ°æŶåĢĻ
    -0.09
    shire
    -0.09
    ìĦ
    -0.09
    é¹Ĭ
    -0.09
    rotch
    -0.08
    POSITIVE LOGITS
    å°ıäºĭ
    0.10
    çĺŁ
    0.09
    urn
    0.09
    éĶŃ
    0.09
    åħ¬åħ±èµĦæºIJ
    0.08
    opic
    0.08
    åĵī
    0.08
    ocratic
    0.08
    aped
    0.08
    沧
    0.08
    Activations Density 0.065%

    No Known Activations