© 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. 53676
    Prev
    Next
    INDEX
    Explanations

    Miss, MS, Branch, Oxford, Texarkana

    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
    èĪ¹ä¸Ĭ
    -0.08
    延éķ¿
    -0.08
    bie
    -0.08
    orb
    -0.08
    ary
    -0.08
    éĹ»
    -0.07
    held
    -0.07
    bulk
    -0.07
    IPPING
    -0.07
    flux
    -0.07
    POSITIVE LOGITS
    妲
    0.10
    æ§Ľ
    0.10
    æĪijå¦Ī
    0.09
    สà¸Ķ
    0.09
    azz
    0.09
    çĿ«
    0.09
    é£ŁåłĤ
    0.09
    ers
    0.09
    èĩªé©¾
    0.09
    essions
    0.09
    Activations Density 0.001%

    No Known Activations