© 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. 53125
    Prev
    Next
    INDEX
    Explanations

    ease and difficulty

    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
    pte
    -0.09
    çĩĥæ°Ķ
    -0.08
    umed
    -0.08
     ca
    -0.08
     Böl
    -0.08
    ableView
    -0.08
    çĶµåĻ¨
    -0.08
    æĹłåı¯
    -0.08
    èļ©
    -0.08
     br
    -0.08
    POSITIVE LOGITS
    ä¸Ķ
    0.10
    à¹ģà¸ĸม
    0.09
    à¸Ľà¸£à¸²
    0.09
    ç¡ķ士åѦä½į
    0.09
    _timing
    0.09
    æŃĩ
    0.09
    èĤĺ
    0.09
    å¯Įæľī
    0.09
    imson
    0.08
     Granite
    0.08
    Activations Density 0.184%

    No Known Activations