© 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. 27641
    Prev
    Next
    INDEX
    Explanations

    cost-effective or efficient

    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
    ocker
    -0.10
    äºĽä»Ģä¹Ī
    -0.08
    acha
    -0.08
    峡
    -0.08
    æĤłæĤł
    -0.08
    ober
    -0.08
    ences
    -0.08
    iability
    -0.08
    /her
    -0.08
    pes
    -0.08
    POSITIVE LOGITS
    çľģéĴ±
    0.11
    åĢļ
    0.09
    å®ŀæĥł
    0.09
    space
    0.09
    tron
    0.09
    ä¹ĭéģĵ
    0.09
    éĢĶ
    0.09
    空éĹ´
    0.09
    å°ijåIJĥ
    0.09
     solución
    0.09
    Activations Density 0.037%

    No Known Activations