© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    baseball innings

    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
    ฯ
    -0.11
    ilon
    -0.11
    è¿Ħ
    -0.10
    é£ŀæī¬
    -0.10
    å¥ģ
    -0.10
    åĬ¨çĶŁæĪIJ
    -0.09
    çģµåĬ¨
    -0.09
    åĪİ
    -0.09
    åĪ©äºļ
    -0.09
    oS
    -0.09
    POSITIVE LOGITS
    ormal
    0.09
    pd
    0.09
    以ä¸ĬçļĦ
    0.09
    halt
    0.09
    ro
    0.09
    /out
    0.08
    mun
    0.08
    éĻIJãĤĬ
    0.08
    ãģĹãģ¾ãģĨ
    0.08
    çļĦåħ³æ³¨
    0.08
    Activations Density 0.002%

    No Known Activations