© 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. 22413
    Prev
    Next
    INDEX
    Explanations

    Casper, Casablanca, CAS9

    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
    thing
    -0.10
    edor
    -0.09
    à°¡
    -0.09
    å½ĵä¹ĭ
    -0.09
    een
    -0.09
    edly
    -0.09
    sic
    -0.09
    CTION
    -0.09
    åı»
    -0.08
    snap
    -0.08
    POSITIVE LOGITS
    cade
    0.13
    åŃIJéĩĮ
    0.11
    ties
    0.10
    uate
    0.10
    iers
    0.10
    umpt
    0.09
    idon
    0.09
    	TokenName
    0.09
    è§İ
    0.09
     overst
    0.08
    Activations Density 0.031%

    No Known Activations