© 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. 48669
    Prev
    Next
    INDEX
    Explanations

    fiscal year, cliff, responsibility, health

    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
    од
    -0.09
    делÑĮ
    -0.09
    atter
    -0.09
    åĴĮæĶ¯æĮģ
    -0.09
    åı°è¯į
    -0.08
    esch
    -0.08
    åĴĮåľ°åĮº
    -0.08
    enu
    -0.08
    Spe
    -0.08
    AINER
    -0.08
    POSITIVE LOGITS
    ally
    0.10
    icious
    0.10
    ×ķף
    0.09
    rary
    0.09
     minded
    0.09
    mente
    0.09
    ALLY
    0.09
    è¿ĺ好
    0.09
    inct
    0.09
    éļ¾æĢª
    0.09
    Activations Density 0.007%

    No Known Activations