© 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. 23833
    Prev
    Next
    INDEX
    Explanations

    Redevelopment

    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
    马æĭī
    -0.10
    ãģªãĤĭ
    -0.10
    оÑģÑĮ
    -0.09
    ARAM
    -0.09
    ðŁĶį
    -0.09
    anness
    -0.09
    ILON
    -0.09
    akk
    -0.09
    IMITIVE
    -0.09
    szed
    -0.09
    POSITIVE LOGITS
    0
    0.09
    2
    0.09
    äºĨåIJ§
    0.09
    åĪ«çļĦ
    0.08
    1
    0.08
    4
    0.08
    éĥħ
    0.08
    é½IJ
    0.08
    3
    0.08
    other
    0.08
    Activations Density 0.315%

    No Known Activations