© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7947
    Prev
    Next
    INDEX
    Explanations

    behind in

    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
    ium
    -0.09
    istic
    -0.09
    uality
    -0.09
    ä¸īæĸ¹
    -0.09
    pto
    -0.09
    çΏ
    -0.09
    oter
    -0.09
    blr
    -0.08
    ä¸įçĦ¶
    -0.08
     bá»ı
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    ðŁı»
    0.10
    ward
    0.10
    ges
    0.09
    æĪĸå¤ļ
    0.09
    æľīèī²
    0.08
    ToFront
    0.08
    jective
    0.08
    åħ¶ä½Ļ
    0.08
    rik
    0.08
    Activations Density 0.009%

    No Known Activations