© 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. 50261
    Prev
    Next
    INDEX
    Explanations

    running, starting, flying, -ing words

    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
    ings
    -0.10
    åĸij
    -0.10
    åŁ
    -0.09
    æ·±æĥħ
    -0.08
    ish
    -0.08
    è¿ijè§Ĩ
    -0.08
    赧
    -0.08
    erm
    -0.08
    æ±ĩ
    -0.08
     pracy
    -0.08
    POSITIVE LOGITS
    æĬ¬
    0.10
    ness
    0.10
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
    efault
    0.09
    verbosity
    0.09
    æĨij
    0.09
    WSTR
    0.09
    oire
    0.09
     Ethi
    0.09
    æķij
    0.09
    Activations Density 0.125%

    No Known Activations