© 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. 50952
    Prev
    Next
    INDEX
    Explanations

    San Antonio, Texas

    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
    ety
    -0.10
    èĽĻ
    -0.10
    èĭĩ
    -0.09
    ingly
    -0.09
    /vnd
    -0.09
    翦
    -0.09
    森æŀĹ
    -0.09
    orgen
    -0.08
    rious
    -0.08
    ndo
    -0.08
    POSITIVE LOGITS
    çĵ·
    0.10
    æŃ¥æŃ¥
    0.09
    tram
    0.09
    æĦıåij³çĿĢ
    0.09
     Ramp
    0.08
     Maui
    0.08
    éĻ¶çĵ·
    0.08
    éļı
    0.08
    å°ĺ
    0.08
    æħİéĩį
    0.08
    Activations Density 0.035%

    No Known Activations