© 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. 62112
    Prev
    Next
    INDEX
    Explanations

    chord variations, hooks, intro, Rift Valley, Copyright, Order

    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
    apia
    -0.11
    genes
    -0.08
    pta
    -0.08
    ality
    -0.08
    lav
    -0.08
    oya
    -0.08
    åī
    -0.08
    ouve
    -0.08
    ê°IJ
    -0.08
    еÐ
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.12
    alysis
    0.09
    vertise
    0.08
    åħĴ
    0.08
    示èĮĥåŁºåľ°
    0.08
     взÑıÑĤÑĮ
    0.08
    storms
    0.08
    alyzed
    0.08
    ä¹Ĥ
    0.08
     tertiary
    0.08
    Activations Density 0.006%

    No Known Activations