© 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. 56903
    Prev
    Next
    INDEX
    Explanations

    holstered weapon, belt loop, hidden pouch

    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
    .typ
    -0.10
    ç¥Ŀç¦ı
    -0.10
    æģ½
    -0.09
    esting
    -0.09
    ãĤĪãģĨãģ§
    -0.09
    åıĮåIJij
    -0.09
    ç´¢èµĶ
    -0.09
    èĭĩ
    -0.09
    æĬĺåıł
    -0.09
    embre
    -0.09
    POSITIVE LOGITS
    佩
    0.09
    éŀ¬
    0.09
    éħįä¸Ĭ
    0.08
    uby
    0.08
    è´´
    0.08
    åĥļ
    0.08
    èħ°éĥ¨
    0.08
    igel
    0.08
    åħĶ
    0.08
    æ±ŁåĮĹ
    0.08
    Activations Density 0.022%

    No Known Activations