© 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. 21350
    Prev
    Next
    INDEX
    Explanations

    elements 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
    èĶ¼
    -0.10
    è¯Ĥ
    -0.10
    ish
    -0.10
    ability
    -0.10
    erty
    -0.09
    ning
    -0.09
    oka
    -0.09
    ðŁı»
    -0.09
    lix
    -0.09
    ableObject
    -0.09
    POSITIVE LOGITS
     ÑĥпÑĢавлениÑı
    0.11
    áĥĹ
    0.10
    wise
    0.10
    ipse
    0.10
     пиÑĤаниÑı
    0.09
    alist
    0.09
    peror
    0.09
    ucle
    0.09
     Pins
    0.08
    ials
    0.08
    Activations Density 0.057%

    No Known Activations