© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8261
    Prev
    Next
    INDEX
    Explanations

    legal citation numbers

    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
    omb
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    ulp
    -0.09
    ality
    -0.08
    asers
    -0.08
    odore
    -0.08
     barren
    -0.08
     PATCH
    -0.08
    ulent
    -0.08
     delicate
    -0.08
    POSITIVE LOGITS
    è¾ķ
    0.10
    éĻIJæŶ
    0.10
    读åIJİ
    0.10
    å¢ĥåĨħ
    0.09
    ingham
    0.09
    åĻ¤
    0.09
    åĨ¢
    0.09
    åħ±åĪĽ
    0.09
    å¤ļå±Ĥ次
    0.09
    æ³
    0.09
    Activations Density 0.235%

    No Known Activations