© 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. 50776
    Prev
    Next
    INDEX
    Explanations

    related to or connection with

    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
    eon
    -0.10
    borg
    -0.09
    ·»
    -0.09
    uger
    -0.09
    ä¸ĵåĮº
    -0.09
    å¦Ĭ
    -0.08
    ä½ĥ
    -0.08
    UTTON
    -0.08
    angs
    -0.08
    ги
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    ä»»ä½ķ
    0.11
     anything
    0.10
     tin
    0.09
    anything
    0.09
     any
    0.09
    è¡Įä¸ļä¸Ń
    0.09
    é©·
    0.09
    ctest
    0.09
    éģĹ
    0.09
    Activations Density 0.015%

    No Known Activations