© 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. 49424
    Prev
    Next
    INDEX
    Explanations

    gluten-free

    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
    aland
    -0.09
    æ´ŀ
    -0.08
    PropertyParams
    -0.08
    -animate
    -0.08
    é£İåIJ¹
    -0.08
     ÑģмÑĭÑģл
    -0.08
     Sk
    -0.08
    æµĵæµĵçļĦ
    -0.08
    sWith
    -0.08
    _Statics
    -0.08
    POSITIVE LOGITS
    ç¿İ
    0.09
    çĹķ迹
    0.09
    ä¸įæ¸ħ
    0.09
    æ¦ķ
    0.09
    arte
    0.09
    icious
    0.09
    çĹĩ
    0.09
    ente
    0.09
    ated
    0.09
    ather
    0.09
    Activations Density 0.005%

    No Known Activations