© 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. 33654
    Prev
    Next
    INDEX
    Explanations

    other people experiencing same problem

    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
    é£İåIJ¹
    -0.11
    å±Ĥ次
    -0.09
    ImageView
    -0.09
    imd
    -0.09
    åĪĹ
    -0.09
    ТÐŀ
    -0.09
    鬲
    -0.08
    å±ħ
    -0.08
    æļ¹
    -0.08
    èıĬ
    -0.08
    POSITIVE LOGITS
     similar
    0.11
    åĽ°æī°
    0.10
    æĥħåĨµ
    0.10
    Similar
    0.10
    类似
    0.10
    similar
    0.10
    ething
    0.09
    éģŃéģĩ
    0.09
    çĽ¸ä¼¼
    0.09
    æīįæľī
    0.09
    Activations Density 0.078%

    No Known Activations