© 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. 1705
    Prev
    Next
    INDEX
    Explanations

    stents, stand, orbs, cases, exchanges, moms, bridge, jobs, email, locks

    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
    cel
    -0.09
    tur
    -0.09
     gó
    -0.08
    cant
    -0.08
    .kotlin
    -0.08
    çªĿ
    -0.08
    lad
    -0.08
    éo
    -0.08
    -know
    -0.08
    ãĤĴè¡ĮãģĦ
    -0.08
    POSITIVE LOGITS
    åĨ¥
    0.09
    çł´éŨ
    0.09
    æĺĢ
    0.08
    ä¾ĺ
    0.07
    edTextBox
    0.07
    ä¹¾åĿ¤
    0.07
    çļĦ羣å®ŀæĢ§
    0.07
    hand
    0.07
    çĪ±åIJĥ
    0.07
     cosy
    0.07
    Activations Density 0.416%

    No Known Activations