© 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. 3743
    Prev
    Next
    INDEX
    Explanations

    Kh or hab with following syllable

    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
    keit
    -0.09
    eks
    -0.09
    çıij
    -0.09
    edException
    -0.08
    athan
    -0.08
    è´¢åĬĽ
    -0.08
    çĩĬ
    -0.08
    ering
    -0.08
    WithData
    -0.08
     chronic
    -0.08
    POSITIVE LOGITS
    isty
    0.11
    ãģ£ãģ¨
    0.10
    å¥ł
    0.09
    طة
    0.09
    mour
    0.09
    æĭŃ
    0.09
    rist
    0.09
    çĮĹ
    0.09
    OOSE
    0.09
    ience
    0.08
    Activations Density 0.047%

    No Known Activations