© 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. 18766
    Prev
    Next
    INDEX
    Explanations

    basket

    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
    thic
    -0.09
    åĬ¨æľº
    -0.09
    ician
    -0.09
    REN
    -0.09
    andal
    -0.08
    ibus
    -0.08
    eren
    -0.08
    suit
    -0.08
    çģ¿çĥĤ
    -0.08
    eras
    -0.08
    POSITIVE LOGITS
    ieri
    0.11
    tle
    0.10
    çĦ¶æĺ¯
    0.10
    ting
    0.09
    rum
    0.09
    iffs
    0.09
    idge
    0.09
    tings
    0.09
    ry
    0.09
    eer
    0.09
    Activations Density 0.006%

    No Known Activations