© 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. 4864
    Prev
    Next
    INDEX
    Explanations

    orgias The rise of ISIS

    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
    çī¹åĪ«å£°æĺİ
    -0.10
    æĸ¥
    -0.10
    æķ¬
    -0.10
    urre
    -0.10
    寵
    -0.09
    itionally
    -0.09
    .synthetic
    -0.09
    _WEAPON
    -0.09
    身é«ĺ
    -0.09
    ctp
    -0.09
    POSITIVE LOGITS
    饱
    0.09
    ä¼ģ
    0.08
    æĪijä¸į
    0.08
    ç®Ĺæĺ¯
    0.08
     cop
    0.07
    æĪij个人
    0.07
    å·²å®ĮæĪIJ
    0.07
    客
    0.07
    um
    0.07
    çİĩè¾¾
    0.07
    Activations Density 0.407%

    No Known Activations