© 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. 22438
    Prev
    Next
    INDEX
    Explanations

    hiring and recruitment

    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
    reme
    -0.09
    gnu
    -0.09
    ghi
    -0.09
    alte
    -0.09
    adder
    -0.09
    åı¯æĥ³
    -0.09
    orsch
    -0.08
    alnum
    -0.08
     Panc
    -0.08
     маÑĢÑĪ
    -0.08
    POSITIVE LOGITS
    å¡«è¡¥
    0.10
    å¹²éĥ¨
    0.10
    è³¢
    0.09
    è´¤
    0.09
    ep
    0.09
    etat
    0.08
    çĤķ
    0.08
    ä¹°çļĦ
    0.08
    åĴĮåľ°åĮº
    0.08
    bee
    0.08
    Activations Density 0.022%

    No Known Activations