© 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. 29901
    Prev
    Next
    INDEX
    Explanations

    television, cable, coaxial

    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
    apel
    -0.10
    utow
    -0.09
    inspace
    -0.09
    æľºåĻ¨äºº
    -0.09
    模èĮĥ
    -0.09
    å§Ķå±Ī
    -0.09
    Çİ
    -0.09
    -ticket
    -0.09
    bands
    -0.08
    æ¡£
    -0.08
    POSITIVE LOGITS
    éĺĨ
    0.09
    èĦ©
    0.09
     Cannot
    0.08
    ç½į
    0.08
    ç¾
    0.08
    åĽŀé¦Ī
    0.08
    éĨ®
    0.08
    -ste
    0.08
    åĺĽ
    0.08
    åİĨåı²æĸĩåĮĸ
    0.08
    Activations Density 0.152%

    No Known Activations