© 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. 33789
    Prev
    Next
    INDEX
    Explanations

    numbers followed by delimiters, words, or specific numbers

    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
    åij±
    -0.09
    oom
    -0.09
    .ut
    -0.09
    rians
    -0.09
    å¸Ĥä¸Ńå¿ĥ
    -0.09
    uling
    -0.08
    ison
    -0.08
    è£ķ
    -0.08
    gps
    -0.08
    åIJĦèĩªçļĦ
    -0.08
    POSITIVE LOGITS
    éĩįè¦ģåİŁåĽł
    0.09
    åįģä¹Ŀå±Ĭ
    0.09
    åİŁåĽłæĺ¯
    0.09
     Burnett
    0.08
    encial
    0.08
    pons
    0.08
    è¿Ļ段
    0.08
    ä¸Ģ件äºĭæĥħ
    0.08
     commitments
    0.08
    -packages
    0.08
    Activations Density 0.078%

    No Known Activations