© 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. 27353
    Prev
    Next
    INDEX
    Explanations

    taken or taken away

    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
    桦
    -0.10
    åħ¨åijĺ
    -0.10
    赦
    -0.10
    次æķ°
    -0.09
     Swinger
    -0.09
    åħ¼
    -0.09
    èIJ½
    -0.09
    parator
    -0.08
    ów
    -0.08
     ÑģоÑħÑĢани
    -0.08
    POSITIVE LOGITS
    离åİ»
    0.23
    带走
    0.21
    离å¼Ģ
    0.20
    èµ°äºĨ
    0.17
    离å¼ĢäºĨ
    0.16
    éĽ¢éĸĭ
    0.15
    åĩºåİ»
    0.14
    åİ»äºĨ
    0.13
     away
    0.13
    èĢĮåİ»
    0.13
    Activations Density 0.083%

    No Known Activations