© 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. 10029
    Prev
    Next
    INDEX
    Explanations

    like any, like that

    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
    åģ»
    -0.09
    æ®ĥ
    -0.09
    髹
    -0.09
    ä¸ī代
    -0.08
    _defaults
    -0.08
    ä¼Ļä¼´
    -0.08
    æĿ¥çľĭçľĭ
    -0.08
     accompany
    -0.08
    rij
    -0.08
    çĹ
    -0.08
    POSITIVE LOGITS
     anywhere
    0.10
    lemen
    0.09
    è§ģè¿ĩ
    0.09
    eken
    0.09
    åŁł
    0.09
    1
    0.09
    4
    0.09
    3
    0.09
    2
    0.09
    -ms
    0.09
    Activations Density 0.017%

    No Known Activations