© 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. 19623
    Prev
    Next
    INDEX
    Explanations

    millennials and cohort studies

    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
    éĺĴ
    -0.10
    æĺİæľĹ
    -0.09
    ModelAttribute
    -0.09
    ê·¹
    -0.09
     fot
    -0.08
    æ¼Ĩ
    -0.08
    马æĭī
    -0.08
    \-
    -0.08
    otch
    -0.08
     vag
    -0.08
    POSITIVE LOGITS
    çŧ
    0.11
     Sapphire
    0.09
    rop
    0.09
    crow
    0.08
    ipl
    0.08
    å±ģ
    0.08
    placement
    0.08
    IRON
    0.08
    åħ³åĪĩ
    0.08
    gba
    0.08
    Activations Density 0.001%

    No Known Activations