© 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. 38960
    Prev
    Next
    INDEX
    Explanations

    First Amendment speech

    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
    éªŀ
    -0.10
    è°¦
    -0.10
    è·¡
    -0.10
    磾
    -0.09
    æ·
    -0.09
     bölüm
    -0.09
    åį´è¢«
    -0.09
    迹
    -0.08
    ä¿Ŀå®Ī
    -0.08
    èĪĴéĢĤ
    -0.08
    POSITIVE LOGITS
    åĸī
    0.10
     speech
    0.10
    è¨Ģ论
    0.10
    åĴĢ
    0.10
    iphy
    0.10
    沫
    0.09
     censorship
    0.09
     khá»ı
    0.09
     Speech
    0.08
    èĦ±
    0.08
    Activations Density 0.136%

    No Known Activations