© 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. 34887
    Prev
    Next
    INDEX
    Explanations

    in northernin preparationin twoin thein vivo

    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
    _scroll
    -0.09
    mad
    -0.09
    zew
    -0.09
    å°ıçĻ½
    -0.09
     indem
    -0.09
    riba
    -0.09
    cest
    -0.08
    è¹²
    -0.08
    bara
    -0.08
    çĪ½
    -0.08
    POSITIVE LOGITS
    _RUNTIME
    0.10
    åĵªæĢķæĺ¯
    0.10
    被åĬ¨
    0.09
    åħ½
    0.09
    ç¤ģ
    0.09
    åĬ¨éĿĻ
    0.08
    lion
    0.08
     ther
    0.08
    å¯ĵ
    0.08
    æĬĹåĩ»
    0.08
    Activations Density 0.654%

    No Known Activations