© 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. 5608
    Prev
    Next
    INDEX
    Explanations

    best part

    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
    rary
    -0.10
    éģĹ
    -0.09
    naires
    -0.08
    ãģıãĤĬ
    -0.08
    anter
    -0.08
    зам
    -0.08
    åīįæıIJæĺ¯
    -0.08
    纵
    -0.08
     Forg
    -0.08
    gos
    -0.08
    POSITIVE LOGITS
    ibt
    0.09
    åĪ«è¯´
    0.09
    å´´
    0.09
    cord
    0.08
    ket
    0.08
    æĹ¶è¾°
    0.08
     оÑĢигина
    0.08
    apper
    0.08
    绳
    0.08
    itarian
    0.08
    Activations Density 0.026%

    No Known Activations