© 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. 21633
    Prev
    Next
    INDEX
    Explanations

    pursuit 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
    æ¶Į
    -0.10
    ateur
    -0.10
    人å¿ĥ
    -0.10
    ets
    -0.09
    oki
    -0.09
    çķĮçļĦ
    -0.09
    -found
    -0.09
    orges
    -0.09
    orta
    -0.09
    -fashioned
    -0.09
    POSITIVE LOGITS
    able
    0.11
    ably
    0.11
    ively
    0.10
    æŶ髦
    0.09
    ces
    0.09
    äºĨ大éĩıçļĦ
    0.09
    iful
    0.09
    antly
    0.08
    edor
    0.08
    è¹
    0.08
    Activations Density 0.008%

    No Known Activations