© 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. 37420
    Prev
    Next
    INDEX
    Explanations

    logical consequences

    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
    åĪļ好
    -0.09
    iggins
    -0.08
    åIJĪè§Ħ
    -0.08
    æ¬ł
    -0.08
    ç´¯
    -0.08
    ÑĭÑĪ
    -0.07
    reau
    -0.07
    kat
    -0.07
     coinc
    -0.07
    owment
    -0.07
    POSITIVE LOGITS
    ç»ĵ论
    0.12
    éĢ»è¾ij
    0.11
    çŁ¥éģĵèĩªå·±
    0.10
    éĤ
    0.10
    çĶĺ
    0.10
     logically
    0.10
    å¿ħçĦ¶
    0.10
    人æīįéĺŁä¼į
    0.10
    åĢĴ
    0.09
    çµIJ
    0.09
    Activations Density 0.057%

    No Known Activations