© 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. 20151
    Prev
    Next
    INDEX
    Explanations

    print function calls and outputting information

    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
    ally
    -0.11
    hr
    -0.10
    涯
    -0.10
    ãģ¶ãĤĬ
    -0.09
    ement
    -0.09
    çĪ¿
    -0.09
    naire
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    çªģå¦Ĥåħ¶
    -0.08
    rag
    -0.08
    POSITIVE LOGITS
    outs
    0.16
    ables
    0.13
    绶
    0.12
    ABLE
    0.11
    erv
    0.11
    able
    0.10
    ableObject
    0.10
    out
    0.10
    º
    0.10
    making
    0.09
    Activations Density 0.082%

    No Known Activations