© 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. 6918
    Prev
    Next
    INDEX
    Explanations

    chess notations and positions

    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
    atu
    -0.10
    ç»Ĩå¾®
    -0.10
     pict
    -0.10
    lus
    -0.09
    Binder
    -0.08
    _TUN
    -0.08
    åĨ¶éĩij
    -0.08
    ç³ģ
    -0.08
    çĶľç¾İ
    -0.08
    _NC
    -0.08
    POSITIVE LOGITS
    æĮº
    0.10
    è°£
    0.10
    askan
    0.09
    éĢĢ
    0.09
    validator
    0.09
    _ly
    0.09
    .lp
    0.08
    èĨ³
    0.08
     Buckley
    0.08
    èĤª
    0.08
    Activations Density 0.012%

    No Known Activations