© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36603
    Prev
    Next
    INDEX
    Explanations

    doping in sports

    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
    åı
    -0.10
    éŨåīį
    -0.10
    oft
    -0.09
    -eng
    -0.08
    ewise
    -0.08
    æĥłæ°ij
    -0.08
    çĶ¦
    -0.08
    æŀĦæĢĿ
    -0.08
    _printer
    -0.08
    åĬŀåħ¬
    -0.08
    POSITIVE LOGITS
    ä½ľå¼Ĭ
    0.13
    害
    0.12
    åī½
    0.12
    è¿Ŀè§Ħ
    0.11
    举æĬ¥
    0.11
    红线
    0.11
    è¶ħæłĩ
    0.10
    严
    0.10
    èĬ±æł·
    0.09
    æŁ¥å¤Ħ
    0.09
    Activations Density 0.048%

    No Known Activations