© 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. 55695
    Prev
    Next
    INDEX
    Explanations

    studying at a university or school

    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
    ä¿Ł
    -0.09
    -placeholder
    -0.09
    个å¤ļ
    -0.08
    éĢµ
    -0.08
    çĵ·
    -0.08
    海滨
    -0.08
    注æĺİåĩºå¤Ħ
    -0.08
     singular
    -0.08
    åıĮéĩį
    -0.08
    -entry
    -0.08
    POSITIVE LOGITS
    å¿«æĬ¥
    0.09
    facts
    0.09
    è§ľ
    0.09
    é¦ĸéĢī
    0.09
    .Modules
    0.08
    泫
    0.08
    rium
    0.08
    åıijæī¬
    0.08
     magna
    0.08
    endir
    0.08
    Activations Density 0.023%

    No Known Activations