© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61054
    Prev
    Next
    INDEX
    Explanations

    contains affiliate links

    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
    imately
    -0.09
    à¹ĥหà¸į
    -0.09
    lear
    -0.09
    èĥ½æī¾åĪ°
    -0.08
     soph
    -0.08
    é¦
    -0.08
     simulator
    -0.08
    Comple
    -0.08
    èģĶéĢļ
    -0.08
    åĩ¡äºĭ
    -0.08
    POSITIVE LOGITS
    对ä»ĸ
    0.11
    åīįæīĢ
    0.09
    对åħ¶
    0.09
    许å¤ļ
    0.09
    严èĤĥ
    0.09
    /Runtime
    0.09
    äºĨ许å¤ļ
    0.09
    ä½łä¹Ł
    0.08
    æīĢè°ĵçļĦ
    0.08
    ä¸Ńå¤ĸ
    0.08
    Activations Density 0.019%

    No Known Activations