© 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. 55194
    Prev
    Next
    INDEX
    Explanations

    Whitney Point, LLP, embedding

    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
    stu
    -0.09
    ateur
    -0.09
    æŶåĢĻ
    -0.08
    åĩºå¤Ħ
    -0.08
    ÑĥÑĪки
    -0.08
    teen
    -0.08
    intosh
    -0.08
    usterity
    -0.08
    uset
    -0.08
    st
    -0.08
    POSITIVE LOGITS
    tics
    0.10
    ilde
    0.09
    å¨ħ
    0.09
    é»ĺé»ĺåľ°
    0.09
    æł¼å°Ķ
    0.09
    eker
    0.09
    tic
    0.09
    æµĴ
    0.09
    éĢ¸
    0.09
    ä¼ļéķ¿
    0.09
    Activations Density 0.001%

    No Known Activations