© 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. 48259
    Prev
    Next
    INDEX
    Explanations

    kilometers and square kilometers

    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
    éĩijéĴ±
    -0.10
    iez
    -0.10
    çī¢åĽº
    -0.09
    ç½²
    -0.09
    ilde
    -0.09
    apy
    -0.09
    ç»Ħç»ĩçĶŁæ´»
    -0.09
    à¸ij
    -0.09
    æĬµ
    -0.09
    èĩ´æķ¬
    -0.09
    POSITIVE LOGITS
    èĮĥ
    0.08
    ãģļ
    0.08
    tml
    0.08
    unes
    0.08
    shi
    0.08
    åľ¨æĪij
    0.08
    per
    0.08
    arta
    0.08
     Cry
    0.08
    oru
    0.08
    Activations Density 0.017%

    No Known Activations