© 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. 7683
    Prev
    Next
    INDEX
    Explanations

    congratulations or greetings

    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
    åı¯æĥľ
    -0.12
    ç´§æİ¥çĿĢ
    -0.09
    åħ¨å¥Ĺ
    -0.09
    åħ´å¥ĭ
    -0.09
    çģ«çĥ§
    -0.09
    zing
    -0.09
    /column
    -0.08
     ÑĢÑĭ
    -0.08
    åĩ¶
    -0.08
    mux
    -0.08
    POSITIVE LOGITS
    ce
    0.10
    寮
    0.09
    itable
    0.08
    ced
    0.08
    alty
    0.08
    движ
    0.08
     latter
    0.08
    деж
    0.08
    reta
    0.08
    åľ¨æĪijçļĦ
    0.08
    Activations Density 0.015%

    No Known Activations