© 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. 57332
    Prev
    Next
    INDEX
    Explanations

    devices, phone, computer, mouse

    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
    éĻ¢
    -0.10
    çīĻ
    -0.09
    apter
    -0.09
    楼ä¸Ĭ
    -0.09
    afil
    -0.09
    ä¸įç®¡ä½ł
    -0.08
    çĶ¨é¤IJ
    -0.08
    _fp
    -0.08
    åħīè¾ī
    -0.08
    warts
    -0.08
    POSITIVE LOGITS
    èŀŃ
    0.09
    躺çĿĢ
    0.09
    ä¸Ģ大åłĨ
    0.09
    çķĮéĿ¢
    0.09
    ä¸ĬçļĦ
    0.08
    /google
    0.08
    -capital
    0.08
    FRING
    0.08
    çŃīçĿĢ
    0.08
    æĺ¥è¿IJ
    0.08
    Activations Density 0.048%

    No Known Activations