© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22666
    Prev
    Next
    INDEX
    Explanations

    chemical composition

    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
    å¨ģ
    -0.09
    ewater
    -0.09
    LastError
    -0.09
    伤çĹħ
    -0.09
    å¹³æķ´
    -0.09
    tı
    -0.08
    ä¿¡å¿ĥ
    -0.08
    è´«åĽ°åľ°åĮº
    -0.08
    åIJ±
    -0.08
    çģ¾å®³
    -0.08
    POSITIVE LOGITS
    éºĿ
    0.10
    éĨĩ
    0.10
    éħ¯
    0.10
    ogan
    0.08
    è§ħ
    0.08
    áĢļ
    0.08
    shal
    0.08
    岫
    0.08
    stant
    0.08
    кÑĥ
    0.08
    Activations Density 0.038%

    No Known Activations