© 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. 18401
    Prev
    Next
    INDEX
    Explanations

    sports positions

    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
    强çĥĪ
    -0.11
    ä½Ĩæĺ¯å¯¹äºİ
    -0.10
    ivalence
    -0.09
    ä¾ĭå¤ĸ
    -0.09
    ationally
    -0.09
    åijĬè¯īä»ĸ
    -0.09
    alley
    -0.09
    æĦł
    -0.09
    æĹ¶è¾°
    -0.09
    èĦ¯
    -0.09
    POSITIVE LOGITS
    enz
    0.09
    çĬĩ
    0.09
    åĪ°ä½į
    0.08
    TECT
    0.08
    ama
    0.08
    pte
    0.08
    ench
    0.08
    GCC
    0.08
    çīĽ
    0.08
    èĬĤ
    0.08
    Activations Density 0.003%

    No Known Activations