© 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. 62621
    Prev
    Next
    INDEX
    Explanations

    why i said

    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
    éĻįå¹ħ
    -0.10
    éĥ¨å§Ķ
    -0.10
    ä¿Ĺ称
    -0.09
    çĦIJ
    -0.09
    鸨
    -0.09
    ä¿ĥ使
    -0.09
    èĢģæŧå°ıåĮº
    -0.09
    å¥ĩèij©
    -0.09
    èĢģçĪ¸
    -0.08
    ç°Į
    -0.08
    POSITIVE LOGITS
    å¤ĸåĽ½
    0.09
    妹
    0.09
    å²ģæŶ
    0.09
    èŀį
    0.08
     оÑĦоÑĢм
    0.08
    æĺ¯å¾Ī
    0.08
     Lambert
    0.08
    ARK
    0.08
    å§ĭ
    0.08
    quine
    0.08
    Activations Density 0.077%

    No Known Activations