© 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. 62899
    Prev
    Next
    INDEX
    Explanations

    formats, floor, titles, damage

    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
    ock
    -0.10
    (pb
    -0.09
    eph
    -0.08
    fram
    -0.08
    ancestor
    -0.08
    çIJ¦
    -0.08
    pu
    -0.08
     ÑģоÑĤ
    -0.08
    IOC
    -0.08
     اÙĦبÙĦ
    -0.07
    POSITIVE LOGITS
    æĹłå¥Ī
    0.09
    ÙĴ
    0.09
    _sess
    0.09
    olla
    0.09
    .opens
    0.09
    çĻ½éĵ¶
    0.08
    èķĥ
    0.08
    侥幸
    0.08
    juan
    0.08
    cha
    0.08
    Activations Density 0.584%

    No Known Activations