© 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. 7017
    Prev
    Next
    INDEX
    Explanations

    playing games

    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
    strt
    -0.10
    umba
    -0.09
    _stamp
    -0.09
    åĨ¶éĩij
    -0.09
    orie
    -0.09
    çł´
    -0.09
    è¡Įèµ°
    -0.09
    以ä¸ĭæĺ¯
    -0.08
    éĢĥ
    -0.08
    å·¥ä½ľå²Ĺä½į
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽ¢
    0.11
    称ä¹ĭ
    0.09
    _DST
    0.09
    以èĩ´
    0.08
    ogl
    0.08
    æ±²
    0.08
     thủy
    0.08
    din
    0.08
     din
    0.08
    decoded
    0.08
    Activations Density 0.028%

    No Known Activations