© 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. 51615
    Prev
    Next
    INDEX
    Explanations

    debates, fools, system, circus, conscience, rule

    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
    iless
    -0.10
    antar
    -0.10
    ocity
    -0.09
    alers
    -0.09
    اج
    -0.09
     TILE
    -0.08
    æĶ¹åĸĦ
    -0.08
    appable
    -0.08
    _PRESENT
    -0.08
    ILES
    -0.08
    POSITIVE LOGITS
    ç¬ijè¯Ŀ
    0.10
    ç®Ģ缴æĺ¯
    0.10
    ä¸ĢåĽ¢
    0.10
    轻轻
    0.10
    è½»
    0.10
    ç®Ģ缴
    0.09
    èĤ¤
    0.09
    å¼Ģçİ©ç¬ij
    0.09
    åħ¬çĦ¶
    0.09
    çİ·
    0.09
    Activations Density 0.063%

    No Known Activations