© 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. 62434
    Prev
    Next
    INDEX
    Explanations

    negative emotions and concepts

    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
    è´Ń车
    -0.09
    adi
    -0.09
    åįij
    -0.08
    elli
    -0.08
    èĢĥæŁ¥
    -0.08
    红è±Ĩ
    -0.08
    iated
    -0.08
    aci
    -0.08
     Mein
    -0.08
    _BC
    -0.08
    POSITIVE LOGITS
    åľ¨äºİ
    0.13
    å°±åľ¨äºİ
    0.12
    æīĢåľ¨
    0.10
    èݨ
    0.09
    ittel
    0.09
    侥幸
    0.09
    _ASSUME
    0.09
    åįĵè¶Ĭ
    0.09
    æĪijä¸Ģ缴
    0.09
    æĹ¶è¾°
    0.09
    Activations Density 0.134%

    No Known Activations