© 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. 32751
    Prev
    Next
    INDEX
    Explanations

    self reference

    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
    éĢĨåĬ¿
    -0.10
    é³Ĭ
    -0.10
    ä¼ĹæīĢ
    -0.10
    portun
    -0.10
    èĽ°
    -0.10
    åĨħåľ¨
    -0.10
     Blast
    -0.10
    OffsetTable
    -0.10
    åħ´èĩ´
    -0.10
    å³»
    -0.10
    POSITIVE LOGITS
     whether
    0.10
    cro
    0.08
    _tm
    0.08
    ocular
    0.07
    à¹Ģศ
    0.07
    lee
    0.07
    whether
    0.07
    åIJ§
    0.07
     bottoms
    0.07
    entic
    0.07
    Activations Density 0.003%

    No Known Activations