© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    required

    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
    ä¼łå¯¼
    -0.09
    rollable
    -0.09
     sedan
    -0.08
    ableView
    -0.08
    andel
    -0.08
    é«¡
    -0.08
    (clone
    -0.08
    bau
    -0.08
    éķ¿è¿ľ
    -0.08
    ением
    -0.08
    POSITIVE LOGITS
    çĶľçĶľ
    0.10
    è¡Įä¸ļä¸Ń
    0.09
    èĤ¤
    0.09
    åĢŁåı£
    0.09
    æŀ
    0.09
    æijĩ
    0.08
    å°±çŁ¥éģĵ
    0.08
     duct
    0.08
    çīĩåĪ»
    0.08
    åŃ°
    0.08
    Activations Density 0.020%

    No Known Activations