© 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. 26666
    Prev
    Next
    INDEX
    Explanations

    without warranty

    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
    åľ¨ä»ĸçļĦ
    -0.09
    olu
    -0.09
    PASS
    -0.09
    PEAT
    -0.09
    åģķ
    -0.09
    åĽĽåij¨
    -0.09
    åĹħ
    -0.09
    ॥
    -0.09
    afen
    -0.09
    plings
    -0.08
    POSITIVE LOGITS
     remot
    0.09
    主è¦ģåĨħ容
    0.08
     Henderson
    0.08
    åĢ¬
    0.07
    té
    0.07
    Vs
    0.07
    .AC
    0.07
    ãĤ¶
    0.07
    ech
    0.07
     spa
    0.07
    Activations Density 1.917%

    No Known Activations