© 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. 36274
    Prev
    Next
    INDEX
    Explanations

    moving forward

    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
    antor
    -0.10
    ieder
    -0.10
    uspend
    -0.10
    çĸĻ
    -0.10
    oyer
    -0.09
    ifying
    -0.09
    çĦ¶æĺ¯
    -0.09
    æŸ
    -0.09
    itian
    -0.09
    erry
    -0.09
    POSITIVE LOGITS
    mente
    0.12
    -thinking
    0.12
    hin
    0.10
    /back
    0.10
    swith
    0.09
    ism
    0.09
    land
    0.09
    erset
    0.09
    [OF
    0.09
    uns
    0.09
    Activations Density 0.022%

    No Known Activations