© 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. 56030
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    oon
    -0.10
    Tan
    -0.09
    蹶
    -0.09
    樽
    -0.08
    issen
    -0.08
    oving
    -0.08
    rip
    -0.08
    è§ĸ
    -0.08
    eton
    -0.08
     Tan
    -0.08
    POSITIVE LOGITS
    åĽ´
    0.10
    boro
    0.09
    _mono
    0.09
    _mB
    0.09
    quential
    0.09
    åľį
    0.08
    诵
    0.08
    utorial
    0.08
    é«ĺä½į
    0.08
    æĺ¥ç§ĭ
    0.08
    Activations Density 0.001%

    No Known Activations