© 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. 22758
    Prev
    Next
    INDEX
    Explanations

    Greeting/hello

    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
    éĴ»
    -0.09
    ãĥĸãĥ«
    -0.09
    ror
    -0.08
    afi
    -0.08
    éĺİ
    -0.08
    rome
    -0.08
    ling
    -0.08
    å¸ĥ
    -0.08
    ãģĵãģĿ
    -0.08
     ÑįлекÑĤÑĢо
    -0.08
    POSITIVE LOGITS
    ties
    0.10
    INCLUDED
    0.10
    anken
    0.09
    åIJĦä½į
    0.09
    akes
    0.09
    éħĭ
    0.09
    ailer
    0.09
    客
    0.09
    aternity
    0.09
    изаÑĨии
    0.08
    Activations Density 0.013%

    No Known Activations