© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14372
    Prev
    Next
    INDEX
    Explanations

    pH and alkalinity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    âīĤ
    -0.20
    .getInfo
    -0.20
    otine
    -0.20
    éĢŁåº¦
    -0.20
    æįĨ
    -0.20
    åĪĨåī²
    -0.19
    ength
    -0.19
    =size
    -0.19
    hor
    -0.19
    æįĨç»ij
    -0.19
    POSITIVE LOGITS
     pH
    0.34
     neutral
    0.27
    neutral
    0.27
    Neutral
    0.25
    -neutral
    0.25
     neutrality
    0.24
    åŁºè°ĥ
    0.23
    è°ĥèĬĤ
    0.22
    平衡
    0.22
     alkal
    0.21
    Activations Density 0.136%

    No Known Activations