© 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. 35468
    Prev
    Next
    INDEX
    Explanations

    media and press scrutiny

    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
    ä½ıå®ħ
    -0.09
    ÐķÐĿ
    -0.09
    è°¦
    -0.09
    onio
    -0.09
    PREC
    -0.09
    ç½®ä¸ļ
    -0.09
    çĶŁæ´»ä¹łæĥ¯
    -0.09
    _launcher
    -0.09
    çĶ·åŃIJ
    -0.09
    ä¸ķ
    -0.09
    POSITIVE LOGITS
    åªĴä½ĵ
    0.13
     media
    0.12
    æijĦåĥı
    0.12
     press
    0.11
     scrutiny
    0.11
     pes
    0.10
    çļĦåĪ°æĿ¥
    0.10
    åħ¬ä¼Ĺ
    0.10
    åĪ°æĿ¥
    0.10
    æĸ°éĹ»è®°èĢħ
    0.09
    Activations Density 0.217%

    No Known Activations