© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21185
    Prev
    Next
    INDEX
    Explanations

    look for

    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
    orough
    -0.09
    窨
    -0.09
    ìĿį
    -0.09
     Knox
    -0.08
    ursive
    -0.08
    èĮĥåĽ´åĨħ
    -0.08
    æĪijä»¬ä¹Ł
    -0.08
    ankan
    -0.08
     getView
    -0.08
    unas
    -0.08
    POSITIVE LOGITS
    еÑĩен
    0.10
    åħ±é¸£
    0.10
    èĮ¬
    0.10
     signs
    0.10
    äºĨä¸Ģä¸ĭ
    0.09
    ç¼ĺ
    0.09
    çģµæĦŁ
    0.09
    ways
    0.09
    ogle
    0.09
    å£ħ
    0.08
    Activations Density 0.030%

    No Known Activations