© 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. 7664
    Prev
    Next
    INDEX
    Explanations

    eh, he, meh

    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
     McMahon
    -0.11
    lite
    -0.10
    æݨ
    -0.09
    èŃ¦ç¤º
    -0.09
    avo
    -0.09
    Lite
    -0.09
    ãģķ
    -0.09
    ally
    -0.08
    æŀģ
    -0.08
    çĪ·
    -0.08
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.09
     Pon
    0.09
    åħ¶ä»ĸåĽ½å®¶
    0.09
    å¿ĥæĢģ
    0.08
    åıijå±ķæ½ľåĬĽ
    0.08
    lers
    0.08
    ields
    0.08
    urnal
    0.08
    sters
    0.08
    zzle
    0.08
    Activations Density 0.007%

    No Known Activations