© 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. 36197
    Prev
    Next
    INDEX
    Explanations

    covering topics

    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
    pector
    -0.09
    ä¸įçĦ¶
    -0.09
    istic
    -0.09
    [](
    -0.09
    erness
    -0.09
    obi
    -0.09
    apolis
    -0.09
    -license
    -0.09
    swire
    -0.09
    _READONLY
    -0.08
    POSITIVE LOGITS
    tures
    0.12
    TURE
    0.10
    ings
    0.10
     Arb
    0.10
    çķ´
    0.09
    heard
    0.09
    riculum
    0.09
    ials
    0.08
    çİĩè¾¾
    0.08
    ANCE
    0.08
    Activations Density 0.038%

    No Known Activations