© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7663
    Prev
    Next
    INDEX
    Explanations

    Oracle

    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
    sa
    -0.09
    æĦł
    -0.09
    沿线
    -0.09
    orm
    -0.09
    aving
    -0.08
    ster
    -0.08
    马äºij
    -0.08
    sel
    -0.08
    æģ½
    -0.08
    æ²īéĩį
    -0.08
    POSITIVE LOGITS
    çĹĩ
    0.11
    çĸ¹
    0.11
    keit
    0.11
    ç¤ģ
    0.10
    说æĺ¯
    0.09
     ÑħоÑĩ
    0.09
    itional
    0.09
    loid
    0.09
    iginal
    0.09
    erial
    0.09
    Activations Density 0.005%

    No Known Activations