© 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. 18413
    Prev
    Next
    INDEX
    Explanations

    leading the

    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
    å¼ĥ
    -0.08
    å¤Ħå¤Ħ
    -0.08
    åľºåľ°
    -0.08
    æĺ¶
    -0.08
    åĬłä»¥
    -0.08
    izzo
    -0.08
    延å®ī
    -0.08
    /misc
    -0.08
    æĭīåĬ¨
    -0.08
    ÄĻd
    -0.08
    POSITIVE LOGITS
    èħ¥
    0.10
    DEC
    0.09
     khá»ıi
    0.09
    ком
    0.09
    èľķ
    0.08
    chg
    0.08
    åıĺéĿ©
    0.08
     Pierce
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    éĢ¢
    0.08
    Activations Density 0.077%

    No Known Activations