© 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. 19865
    Prev
    Next
    INDEX
    Explanations

    distribution of

    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
    å³¥
    -0.10
    ouro
    -0.10
    åĩºå¤Ħ
    -0.10
    çĴ
    -0.09
    uplicates
    -0.09
    ÑĦикÑģ
    -0.09
    ãģ»ãģĨ
    -0.08
     Utt
    -0.08
    ifies
    -0.08
    otas
    -0.08
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.14
    ally
    0.14
    ively
    0.13
    alm
    0.09
    ustr
    0.09
    éĹ³
    0.09
    ç²¹
    0.09
    inct
    0.09
    KeyCode
    0.09
    onium
    0.09
    Activations Density 0.093%

    No Known Activations