© 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. 7976
    Prev
    Next
    INDEX
    Explanations

    let go

    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
    ise
    -0.09
    åIJ¯
    -0.08
    ãģ¹ãģį
    -0.08
    kins
    -0.08
    毫
    -0.08
    izens
    -0.08
    帻
    -0.08
    å®īçĦ¶
    -0.08
    set
    -0.08
    æ·±åĮĸæĶ¹éĿ©
    -0.08
    POSITIVE LOGITS
    FLOAT
    0.09
    æīĭä¸ŃçļĦ
    0.09
    追æ±Ĥ
    0.09
     grazing
    0.09
    opher
    0.09
    íĮ¡
    0.09
    ç¼°
    0.08
    ľ
    0.08
    ÐĿÐķ
    0.08
    å¤ļä½ĻçļĦ
    0.08
    Activations Density 0.003%

    No Known Activations