© 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. 36409
    Prev
    Next
    INDEX
    Explanations

    blade implants, servers, or game

    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
    à¨Ĩ
    -0.11
    dr
    -0.10
    orer
    -0.10
    duc
    -0.10
    ied
    -0.09
    æĶĺ
    -0.09
    âĶģâĶģ
    -0.09
    apia
    -0.08
    âĸ¾
    -0.08
    ãĤĽ
    -0.08
    POSITIVE LOGITS
    unner
    0.11
     thơ
    0.11
    é©·
    0.10
    less
    0.10
    çīĩåŃIJ
    0.10
     ë¶Ī구íķĺê³ł
    0.09
    arity
    0.09
    0.09
    leted
    0.09
    ics
    0.09
    Activations Density 0.015%

    No Known Activations