© 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. 36416
    Prev
    Next
    INDEX
    Explanations

    Bazaar

    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®ĿçŁ³
    -0.11
    æıĨ
    -0.10
    å³»
    -0.09
    onis
    -0.09
    èĩªæŁ¥
    -0.09
    åĬłå¿«åıijå±ķ
    -0.09
     killer
    -0.09
    agra
    -0.08
    ç¬Ķ
    -0.08
    å®£ä¼łæķĻèĤ²
    -0.08
    POSITIVE LOGITS
    好å¤Ħ
    0.09
    iband
    0.09
    quate
    0.08
    ÐĿÐŀ
    0.08
    egis
    0.08
    æŀĦ
    0.08
    icom
    0.08
    BOSE
    0.08
    çĽĸ
    0.08
    -types
    0.08
    Activations Density 0.002%

    No Known Activations