© 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. 58539
    Prev
    Next
    INDEX
    Explanations

    home or house location

    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
    æĬĬæı¡
    -0.09
    åĽ½å®ī
    -0.09
    .lambda
    -0.09
    å®Ŀå®Ŀ
    -0.08
     REPL
    -0.08
    å¡«è¡¥
    -0.08
    äºĴèģĶäºĴéĢļ
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
     окÑĢÑĥ
    -0.08
    羣åģĩ
    -0.08
    POSITIVE LOGITS
    èµĸ以
    0.10
    åİŁæĿ¥
    0.09
    鼶è·Ŀ离
    0.09
     econom
    0.09
    æĺĶæĹ¥
    0.09
    èĢĮæĪIJ
    0.09
    åİŁæĿ¥çļĦ
    0.09
    Wer
    0.09
    estre
    0.09
    ä¸įè¿ľ
    0.09
    Activations Density 0.040%

    No Known Activations