© 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. 23665
    Prev
    Next
    INDEX
    Explanations

    "too" or "well"

    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
    Cog
    -0.09
    Guest
    -0.09
    ì¶ķ
    -0.08
    رÙĬÙĥ
    -0.08
    ILLA
    -0.08
    ÙĨÙĩ
    -0.08
    guest
    -0.08
    íľĺ
    -0.08
     Davidson
    -0.08
    eko
    -0.08
    POSITIVE LOGITS
    æ¼Ĥ
    0.10
     Bris
    0.09
    eroon
    0.09
    ä¸ĩéĩĮ
    0.09
    ä¹Łå¾Ī
    0.09
    OSC
    0.09
    æ¼Ĥæµģ
    0.08
     Morse
    0.08
     transl
    0.08
    è¾Ī
    0.08
    Activations Density 0.063%

    No Known Activations