© 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. 57442
    Prev
    Next
    INDEX
    Explanations

    XML DOCTYPE declarations

    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
    è¸Į
    -0.09
    ä¹IJæĦı
    -0.09
    edback
    -0.09
     hete
    -0.08
     Carlson
    -0.08
    nos
    -0.08
     Jet
    -0.08
    祼
    -0.08
    estroy
    -0.08
    æĶ¶åĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    aida
    0.11
    /owl
    0.09
    çĶ»å®¶
    0.09
    лан
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.09
    annel
    0.08
    ì°©
    0.08
    åŀŃ
    0.08
    佩æľį
    0.08
    åŀĮ
    0.08
    Activations Density 0.331%

    No Known Activations