© 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. 18356
    Prev
    Next
    INDEX
    Explanations

    flexible and flexibility

    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
    bling
    -0.09
    sville
    -0.09
    ers
    -0.08
    enance
    -0.08
    inals
    -0.08
    lined
    -0.08
    wer
    -0.08
    ing
    -0.08
    el
    -0.08
    ilde
    -0.08
    POSITIVE LOGITS
    berra
    0.11
     mại
    0.10
    teen
    0.10
    grim
    0.10
    è¨ĢãģĪãģ°
    0.10
    ìķµ
    0.10
    -bodied
    0.10
    èĩªå¦Ĥ
    0.09
    èĢĮåıĪ
    0.09
    ãģ«ä¹Ĺ
    0.09
    Activations Density 0.010%

    No Known Activations