© 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. 35204
    Prev
    Next
    INDEX
    Explanations

    hoping for or hoping somebody

    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
    æĢĢæĬ±
    -0.10
    çĹĽèĭ¦
    -0.09
    orf
    -0.09
    æķ¢äºİ
    -0.09
    毫ä¸į
    -0.09
    åİĭè¿«
    -0.08
    orb
    -0.08
    æĤį
    -0.08
    è¿ĻæŶåĢĻ
    -0.08
    bsp
    -0.08
    POSITIVE LOGITS
    lessly
    0.17
    fully
    0.15
    å·²ä¹ħçļĦ
    0.12
     rằng
    0.10
    ãĤĤãģ£ãģ¨
    0.09
    iest
    0.09
    红èĮ¶
    0.09
     ÃŃch
    0.09
     Jahren
    0.09
    è§İ
    0.09
    Activations Density 0.018%

    No Known Activations