© 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. 36943
    Prev
    Next
    INDEX
    Explanations

    similar version variant form

    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
    BUFF
    -0.10
    ç½ħ
    -0.09
    _Tag
    -0.09
    rips
    -0.09
    .tc
    -0.09
    ä¸Ģç³»åĪĹ
    -0.09
    åłµå¡ŀ
    -0.09
    agna
    -0.08
    ç¡
    -0.08
    è¿ĩåī©
    -0.08
    POSITIVE LOGITS
    类似çļĦ
    0.12
     similar
    0.11
     version
    0.11
    çĽ¸ä¼¼
    0.11
    类似
    0.11
    çīĪ
    0.10
    ç»ıçIJĨ
    0.10
    èįIJ
    0.10
     variant
    0.09
    similar
    0.09
    Activations Density 0.283%

    No Known Activations