© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10573
    Prev
    Next
    INDEX
    Explanations

    return on investment or effectiveness

    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
    onth
    -0.10
    ä¸Ńéĵģ
    -0.10
    çĶļèĩ³è¿ŀ
    -0.09
    oded
    -0.09
    isto
    -0.09
    INTERN
    -0.09
    æªĢ
    -0.09
     Mormon
    -0.09
    ikal
    -0.09
    åĤį
    -0.09
    POSITIVE LOGITS
    èļĢ
    0.10
    èĢĥéĩı
    0.09
    ney
    0.09
    nob
    0.09
    emann
    0.09
    htar
    0.08
    è¿Ļç¬Ķ
    0.08
    tement
    0.08
    çİĩ
    0.08
     Masc
    0.08
    Activations Density 0.009%

    No Known Activations