© 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. 37944
    Prev
    Next
    INDEX
    Explanations

    lazy, easy, coward

    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
    monic
    -0.10
    ä¸įæŃ»
    -0.10
    лÑİ
    -0.09
    licos
    -0.08
    ongs
    -0.08
    enties
    -0.08
    碱
    -0.08
    æŃ¡
    -0.08
     FUN
    -0.08
    *out
    -0.08
    POSITIVE LOGITS
    æĩĴ
    0.13
     easier
    0.12
    æį·
    0.12
     coward
    0.11
    便æį·
    0.11
     easy
    0.11
    æĥ«
    0.10
    æķ·
    0.10
    便åĪ©
    0.10
     Lazy
    0.10
    Activations Density 0.065%

    No Known Activations