© 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. 27255
    Prev
    Next
    INDEX
    Explanations

    provided as

    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
    é¦ĸå¸Ń
    -0.09
    éĻĽä¸ĭ
    -0.09
    aintenance
    -0.09
     desert
    -0.09
    è¿İæİ¥
    -0.08
    åĸ³
    -0.08
    èĽ¤
    -0.08
    омн
    -0.08
    硼
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    ä¹ħä¹ħ
    0.09
    abox
    0.09
    å°±ä¸į
    0.09
    jsc
    0.08
    åįĪåIJİ
    0.08
    è¡ĮæĺŁ
    0.08
    oning
    0.08
    tur
    0.08
    ween
    0.08
    è¯ķ
    0.08
    Activations Density 0.067%

    No Known Activations