© 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. 38789
    Prev
    Next
    INDEX
    Explanations

    alkalinity, pH, change

    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
    éĨĴ
    -0.10
    olen
    -0.09
     Cougar
    -0.08
    çķĪ
    -0.08
    ifest
    -0.08
    enberg
    -0.08
    çīµå¼ķ
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    enburg
    -0.08
    ä¼´æľī
    -0.08
    POSITIVE LOGITS
    çıIJ
    0.10
    hum
    0.10
     Hum
    0.10
    å®ŀæķĪ
    0.10
     elit
    0.10
    Hum
    0.10
    å°ī
    0.09
    寿
    0.09
     mant
    0.09
    åįİåįĹ
    0.09
    Activations Density 0.083%

    No Known Activations