© 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. 18184
    Prev
    Next
    INDEX
    Explanations

    fly the flag

    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
    ledge
    -0.09
    ise
    -0.09
    åĪ¨
    -0.08
    è°Ĺ
    -0.08
    å§ĭ
    -0.08
    ware
    -0.08
    æľ«
    -0.08
    åİĭè¿«
    -0.08
     rim
    -0.08
     squ
    -0.08
    POSITIVE LOGITS
    æĹĹ
    0.25
    æĹĹå¸ľ
    0.24
     flags
    0.20
     Flags
    0.19
    å¸ľ
    0.18
    .flags
    0.18
     flag
    0.18
    flags
    0.18
    红æĹĹ
    0.18
    	flags
    0.18
    Activations Density 0.048%

    No Known Activations