© 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. 49998
    Prev
    Next
    INDEX
    Explanations

    hardware partners and expansion

    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
    ä¸İåıijå±ķ
    -0.11
    æĿ²
    -0.10
    íį¼
    -0.10
    æĹłå½¢
    -0.09
    çĪ¹
    -0.09
    rawl
    -0.09
    çĨŁç»ĥ
    -0.09
    éĵ¤
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    nish
    -0.08
    POSITIVE LOGITS
    çĭĹ
    0.09
    iquement
    0.09
    estruct
    0.09
    ETO
    0.09
    onda
    0.09
     ÑĢек
    0.08
     unsub
    0.08
    è¨ŃåĤĻ
    0.08
    设å¤ĩ
    0.08
    çĪ±å¥½èĢħ
    0.08
    Activations Density 0.038%

    No Known Activations