© 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. 11685
    Prev
    Next
    INDEX
    Explanations

    Gabriel and variants

    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
    ings
    -0.10
    Ñģл
    -0.10
    back
    -0.10
     perse
    -0.09
    ör
    -0.09
    ãģĵãģĿ
    -0.09
    羦
    -0.08
    楼ä¸Ĭ
    -0.08
    urret
    -0.08
    楼å±Ĥ
    -0.08
    POSITIVE LOGITS
    bers
    0.10
    ðŁı»
    0.10
    INET
    0.09
    oteca
    0.09
    lict
    0.09
    bies
    0.09
    ually
    0.08
    ¶
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    bing
    0.08
    Activations Density 0.013%

    No Known Activations