© 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. 52133
    Prev
    Next
    INDEX
    Explanations

    reasonable followed by noun/adverb

    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
    rence
    -0.10
    åĿıäºĨ
    -0.09
    è¯Ģ
    -0.08
    rah
    -0.08
    å¿ĥ仪
    -0.08
    aint
    -0.08
    lain
    -0.08
    ç¡®è¯Ĭ
    -0.08
     Brace
    -0.08
    æºŁ
    -0.08
    POSITIVE LOGITS
    -sized
    0.13
    ably
    0.13
     доÑģÑĤаÑĤ
    0.12
     sized
    0.11
    ames
    0.10
    讵
    0.10
    -looking
    0.10
    -priced
    0.10
    pcf
    0.10
    åIJĪçIJĨçļĦ
    0.10
    Activations Density 0.006%

    No Known Activations