© 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. 39375
    Prev
    Next
    INDEX
    Explanations

    staying in touch

    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
    ä¸įåIJ«
    -0.09
    çķļ
    -0.09
    绩
    -0.08
    çķĻåŃĺ
    -0.08
    åīįè¿Ľ
    -0.08
    åºĦ严
    -0.08
    éħĿéħ¿
    -0.08
    è§ģéĿ¢
    -0.08
    rush
    -0.08
    ek
    -0.08
    POSITIVE LOGITS
    çľĭ好
    0.09
    å°½åĬĽ
    0.09
     Rams
    0.08
    nam
    0.08
    tro
    0.08
    åĴĮå°ļ
    0.08
    鸽
    0.08
     dor
    0.08
    Reuse
    0.08
     ram
    0.08
    Activations Density 0.035%

    No Known Activations