© 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. 35282
    Prev
    Next
    INDEX
    Explanations

    made of

    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
    æĹłè®ºæĺ¯åħ¶
    -0.10
    OLOR
    -0.10
    chor
    -0.09
    è°ĥåĬ¨
    -0.09
     каÑĩеÑģÑĤва
    -0.09
    仪
    -0.09
    å¿ĥæĻº
    -0.09
    elve
    -0.08
    arith
    -0.08
    æľĭåıĭåľĪ
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.10
    ä»Ģä¹Īåij¢
    0.09
    çī¹æ®ĬçļĦ
    0.09
    æľĢå¤ļçļĦ
    0.08
    è¿Ļæł·æīįèĥ½
    0.08
    ä»Ģä¹Ī
    0.08
    ong
    0.08
    åIJĮæł·çļĦ
    0.08
    äºĽä»Ģä¹Ī
    0.08
    æ·±åİļçļĦ
    0.08
    Activations Density 0.057%

    No Known Activations