© 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. 22599
    Prev
    Next
    INDEX
    Explanations

    varsity and form

    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
    éļ¼
    -0.09
    æĥij
    -0.09
    pping
    -0.08
    sume
    -0.08
    bourne
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.07
    nego
    -0.07
     ocas
    -0.07
    éĴµ
    -0.07
    ä½ľãĤĬ
    -0.07
    POSITIVE LOGITS
    ities
    0.13
    orld
    0.10
    ity
    0.10
    INGTON
    0.09
    ington
    0.09
    iales
    0.09
    wide
    0.09
    åĴĮåľ°åĮº
    0.09
    ìĶ¬
    0.09
    vanced
    0.09
    Activations Density 0.049%

    No Known Activations