© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22304
    Prev
    Next
    INDEX
    Explanations

    processing something

    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
    CDATA
    -0.11
    aaS
    -0.09
    ãĤĤãģ®ãģ®
    -0.09
    ãĤĤãģ®
    -0.09
    ISTIC
    -0.09
    atu
    -0.09
    管家
    -0.09
    ê¼´
    -0.08
    .matches
    -0.08
    çħ³
    -0.08
    POSITIVE LOGITS
    çĿ¬
    0.10
    è¿Ļ对
    0.10
    sed
    0.09
    ogn
    0.09
    EDURE
    0.09
    泪水
    0.08
    åĪ°çİ°åľ¨
    0.08
    rift
    0.08
    sing
    0.08
    æĶ¾åľ¨
    0.08
    Activations Density 0.063%

    No Known Activations