© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    implications of or for

    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·§
    -0.09
    Jvm
    -0.09
     sop
    -0.08
     Jas
    -0.08
    .Addr
    -0.08
    allet
    -0.08
    å®ķ
    -0.08
    Hack
    -0.08
    Bon
    -0.08
    ÑĪин
    -0.08
    POSITIVE LOGITS
    æ·±è¿ľ
    0.13
    æ·±åĪ»çļĦ
    0.10
    秦çļĩ
    0.10
    åIJİæŀľ
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
     Polic
    0.10
    ÑĥÑĪки
    0.09
    çĶ¬
    0.09
    cust
    0.09
    éĹ³
    0.09
    Activations Density 0.028%

    No Known Activations