© 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. 35309
    Prev
    Next
    INDEX
    Explanations

    boolean expressions or code delimiters

    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
    åĤij
    -0.09
     �
    -0.08
    åĽºçĦ¶
    -0.08
    æľįåĬ¡äºİ
    -0.08
    ________________________________________________________________
    -0.08
    å®ŀåľ¨
    -0.08
    è£ĺ
    -0.08
    说åĪ°è¿ĻéĩĮ
    -0.07
    �
    -0.07
    /entity
    -0.07
    POSITIVE LOGITS
    íĥĪ
    0.09
    èĦ±
    0.09
    aug
    0.09
    ç»Ģ
    0.09
    translator
    0.09
    probe
    0.08
    ìĹIJëĦĪì§Ģ
    0.08
    ä¸Ģ对ä¸Ģ
    0.08
     redes
    0.08
    <decltype
    0.08
    Activations Density 0.342%

    No Known Activations