© 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. 58347
    Prev
    Next
    INDEX
    Explanations

    pH and acid transport

    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
    æ³¥
    -0.10
    éªŀ
    -0.09
    黯
    -0.09
     Vit
    -0.09
    éĺĴ
    -0.08
    ç»IJ
    -0.08
    é²ľè¡Ģ
    -0.08
    两侧
    -0.08
    èĽĬ
    -0.08
    åĪ°æľŁ
    -0.08
    POSITIVE LOGITS
    éħ¸
    0.12
     Humph
    0.09
     Buk
    0.09
    å¸ĥ
    0.09
    åİ»è¿ĩ
    0.09
     pH
    0.08
    FormGroup
    0.08
    INAL
    0.08
     acid
    0.08
    éĤº
    0.08
    Activations Density 0.166%

    No Known Activations