© 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. 51027
    Prev
    Next
    INDEX
    Explanations

    negative states or deficiencies

    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
    æĸ°åĮº
    -0.10
    éľĨ
    -0.10
    Them
    -0.09
    æĹĥ
    -0.09
    çŃ·
    -0.09
     Runtime
    -0.08
    éĺĻ
    -0.08
    /Runtime
    -0.08
    Runtime
    -0.08
    èħ¾
    -0.08
    POSITIVE LOGITS
    umont
    0.10
    ä¸ºçĽ®çļĦ
    0.10
    inx
    0.09
    èĥĥåı£
    0.09
     بÙĪاسطة
    0.09
    aps
    0.09
    æĹ¥çĽĬ
    0.08
    è¿Ļä¹Īä¹ħ
    0.08
    arus
    0.08
     onCreate
    0.08
    Activations Density 0.529%

    No Known Activations