© 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. 32987
    Prev
    Next
    INDEX
    Explanations

    intensifiers before positive adjectives

    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
    å¤ļäºĨ
    -0.11
    ä¸Ģç±»
    -0.10
    å¤ļåIJĥ
    -0.10
    è¶Ĭå¤ļ
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    åŀ¢
    -0.09
    å¤Ħå¤Ħ
    -0.09
    .SIG
    -0.09
    çļĦä¸Ģ项
    -0.09
    åħħ足
    -0.08
    POSITIVE LOGITS
    olly
    0.08
    éĥ¨å§Ķ
    0.08
    ä¾Ŀ次
    0.08
     дог
    0.08
    èĦį
    0.08
     Gene
    0.08
     gene
    0.08
     Möglich
    0.07
    墨西åĵ¥
    0.07
    mark
    0.07
    Activations Density 0.044%

    No Known Activations