© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37216
    Prev
    Next
    INDEX
    Explanations

    guitarist or guitar

    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
    ew
    -0.11
    ëģĶ
    -0.10
    chart
    -0.09
    íĴĪ
    -0.09
    =-=-=-=-=-=-=-=-
    -0.09
    å¿¡
    -0.09
    ç¦ıç¥ī
    -0.09
    epar
    -0.09
    atic
    -0.09
    æł¡åĮº
    -0.09
    POSITIVE LOGITS
    eros
    0.13
    é¾Ħ
    0.10
    eras
    0.10
    çķĮçļĦ
    0.09
    istics
    0.09
    ODE
    0.09
    _BP
    0.09
    ters
    0.09
    erin
    0.09
    keit
    0.09
    Activations Density 0.008%

    No Known Activations