© 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. 53577
    Prev
    Next
    INDEX
    Explanations

    Belmont, Hayward, Belostemma, derivative

    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
    -0.10
    ivor
    -0.10
    å¤ĩ
    -0.09
    çĹĴ
    -0.09
    è¡·
    -0.09
    bing
    -0.08
    æ·Į
    -0.08
    annel
    -0.08
    常å§Ķ
    -0.08
    lsen
    -0.08
    POSITIVE LOGITS
    eros
    0.10
    eer
    0.10
    enegro
    0.10
    sWith
    0.10
    æ¯ı天éĥ½
    0.09
    eurs
    0.09
    ein
    0.09
    ede
    0.09
    åĪ¹è½¦
    0.09
    edy
    0.09
    Activations Density 0.001%

    No Known Activations