© 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. 26559
    Prev
    Next
    INDEX
    Explanations

    if clauses

    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
    åĿł
    -0.09
    _FALL
    -0.09
    梨
    -0.08
    ENTITY
    -0.08
    IEL
    -0.08
    éªļæī°
    -0.08
    è²Į
    -0.08
    uz
    -0.08
    éĤij
    -0.08
    çı©
    -0.08
    POSITIVE LOGITS
     clearer
    0.09
    常æĢģåĮĸ
    0.09
    çIJı
    0.09
    è¿ĺ好
    0.09
    ãģ®ãģ§ãģĻãģĮ
    0.09
    å¼Ł
    0.09
    è´µ
    0.08
    ë¹Ħ
    0.08
    athom
    0.08
    è¿Ħ
    0.08
    Activations Density 0.041%

    No Known Activations