© 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. 55564
    Prev
    Next
    INDEX
    Explanations

    taxes and fees

    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
    æ©¡
    -0.09
    åħ³æ³¨åº¦
    -0.09
    çªĴ
    -0.08
    æł¹æľ¬å°±ä¸į
    -0.08
    对çŃĸ
    -0.08
    iss
    -0.08
    è¶ħæłĩ
    -0.08
    ãĤĭãģŁãĤģãģ«
    -0.08
    TEE
    -0.08
    æĬ¥éħ¬
    -0.08
    POSITIVE LOGITS
    ogg
    0.11
    æĴŃ
    0.09
    éĩİå¤ĸ
    0.09
    ä¸Ģåįĥ
    0.09
    ä¼ļæľī
    0.09
    ä¹ĭç¾İ
    0.08
    ä¸ĢåĪĩ
    0.08
    ipp
    0.08
    æł©
    0.08
    ä¸īçĻ¾
    0.08
    Activations Density 0.010%

    No Known Activations