© 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. 36827
    Prev
    Next
    INDEX
    Explanations

    sleep, production, names

    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
    大人
    -0.12
    è¿ĻçĤ¹
    -0.10
    å¹Ķ
    -0.09
    ĸ
    -0.09
    /cgi
    -0.09
    å¯¹æľªæĿ¥
    -0.09
    обоÑĢоÑĤ
    -0.09
    orton
    -0.09
    ries
    -0.09
    boro
    -0.08
    POSITIVE LOGITS
    pery
    0.09
    ety
    0.09
    ieurs
    0.08
    ãģĹãĤĩãģĨ
    0.08
    ingly
    0.08
    licity
    0.08
    åĦ¿
    0.08
    ting
    0.08
    ett
    0.08
     ’
    0.08
    Activations Density 0.011%

    No Known Activations