© 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. 62405
    Prev
    Next
    INDEX
    Explanations

    left or right side

    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
    äºĨä¸Ģä¸ĭ
    -0.10
    aub
    -0.09
     forth
    -0.09
    窿
    -0.09
    åīįåIJİ
    -0.09
    éĶ±
    -0.08
     Hud
    -0.08
    管å§Ķä¼ļ
    -0.08
     wann
    -0.08
    vie
    -0.08
    POSITIVE LOGITS
    most
    0.13
    -hand
    0.11
    -handed
    0.10
    side
    0.10
    ward
    0.09
    ðŁı»
    0.09
    æĶ¶èĹı
    0.09
    ewood
    0.08
    zeitig
    0.08
    ened
    0.08
    Activations Density 0.038%

    No Known Activations