© 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. 58537
    Prev
    Next
    INDEX
    Explanations

    fluoride and ion compounds

    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
    åĢ¾æĸľ
    -0.10
    åĢ¾
    -0.09
    ä¸įçIJĨ
    -0.09
    伸
    -0.09
    çĥŃ度
    -0.08
    itore
    -0.08
    åĤ¾
    -0.08
     Hollow
    -0.08
    .QueryString
    -0.08
    arton
    -0.08
    POSITIVE LOGITS
    ç»ĪçĶŁ
    0.09
    uffers
    0.09
     fluoride
    0.09
    pitch
    0.09
    辩论
    0.08
     punching
    0.08
    assi
    0.08
     Pitch
    0.08
    ç§ijæĬĢ
    0.08
    inite
    0.08
    Activations Density 0.035%

    No Known Activations