© 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. 51357
    Prev
    Next
    INDEX
    Explanations

    official or formal context words

    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
    urma
    -0.08
    对åºĶçļĦ
    -0.08
    odo
    -0.08
    èĩªèº«çļĦ
    -0.08
    oden
    -0.08
    unct
    -0.08
     ÄIJÃł
    -0.07
    ç©
    -0.07
     cro
    -0.07
    -grand
    -0.07
    POSITIVE LOGITS
    çĶŁæ¶¯
    0.10
    ä¸Ģç±»
    0.09
    åĩłç§į
    0.09
    INAL
    0.09
    åĪ°æľŁ
    0.09
    说åĩºæĿ¥
    0.09
    以èĩ³äºİ
    0.09
    edly
    0.08
    anj
    0.08
    éĤ£ç§į
    0.08
    Activations Density 0.150%

    No Known Activations