© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52378
    Prev
    Next
    INDEX
    Explanations

    qa programs and events

    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
    peria
    -0.09
    èºĩ
    -0.09
    _PLATFORM
    -0.09
    ä»İæѤ
    -0.09
    orgh
    -0.09
    relationships
    -0.09
    ç»ıåİĨ
    -0.09
     Dale
    -0.08
    íĿĶ
    -0.08
    -gnu
    -0.08
    POSITIVE LOGITS
    çŃĶçĸij
    0.11
    æĬ½å¥ĸ
    0.10
    è¯Ĩ
    0.10
    å¸Ń
    0.10
    æĭ©
    0.10
    äºĴåĬ¨
    0.10
    ä¸Ńåľº
    0.09
    è·Ľ
    0.09
    æĬĢèĥ½åŁ¹è®Ń
    0.09
    æ°ij主
    0.09
    Activations Density 0.052%

    No Known Activations