© 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. 33800
    Prev
    Next
    INDEX
    Explanations

    not work properly

    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
    æĩ¦
    -0.10
     trụ
    -0.09
    ceph
    -0.08
    è¿Ļ个éĹ®é¢ĺ
    -0.08
    毫
    -0.08
     Thoughts
    -0.08
    è¿Ļ家åħ¬åı¸
    -0.08
    åįĩèµ·
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    shed
    -0.08
    POSITIVE LOGITS
     fore
    0.10
    æģ°æģ°
    0.09
    å¯Ħ
    0.09
    okies
    0.09
    _poll
    0.08
     Jenner
    0.08
    åħħåĪĨåıijæĮ¥
    0.08
    å½ķ
    0.08
    .OK
    0.08
    æľĢåŁºæľ¬
    0.08
    Activations Density 0.021%

    No Known Activations