© 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. 38695
    Prev
    Next
    INDEX
    Explanations

    take followed by other words

    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
    年人
    -0.09
    soc
    -0.09
    Ã¤ÃŁ
    -0.09
    ç¾¹
    -0.08
     fancy
    -0.08
    odia
    -0.08
    çĦ¶æĺ¯
    -0.08
    ément
    -0.08
    ERGY
    -0.08
    æݧ
    -0.08
    POSITIVE LOGITS
    ABLE
    0.12
    able
    0.10
    aways
    0.10
    abouts
    0.10
    aut
    0.10
    backs
    0.09
    èµİ
    0.09
    ween
    0.09
    lev
    0.08
    offs
    0.08
    Activations Density 0.028%

    No Known Activations