© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8023
    Prev
    Next
    INDEX
    Explanations

    comfortable experience or use

    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
    naire
    -0.10
    оÑĢ
    -0.09
    à¹Į
    -0.09
    çĭIJ
    -0.09
    iers
    -0.09
    èĪ«
    -0.09
    ering
    -0.09
    iors
    -0.09
    ested
    -0.08
    amples
    -0.08
    POSITIVE LOGITS
    ably
    0.13
    -bodied
    0.10
    ment
    0.10
    ëį°
    0.09
    -looking
    0.09
    ément
    0.09
    ä¸İåIJ¦
    0.09
    tics
    0.09
    åĢĺ
    0.09
    ango
    0.09
    Activations Density 0.009%

    No Known Activations