© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51858
    Prev
    Next
    INDEX
    Explanations

    able to

    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
    pher
    -0.10
    s
    -0.10
    ager
    -0.09
    æīĭå¥Ĺ
    -0.08
    adel
    -0.08
    cem
    -0.08
    agers
    -0.08
    n
    -0.08
    sh
    -0.08
     dem
    -0.08
    POSITIVE LOGITS
    èĥľä»»
    0.13
    -bodied
    0.12
    æľīèĥ½åĬĽ
    0.11
    umba
    0.11
    éªĬ
    0.10
    è¿Ļ两ç§į
    0.10
     Ñĥме
    0.10
     вÑĭпÑĥÑģк
    0.10
    verages
    0.09
    çĪ·
    0.09
    Activations Density 0.026%

    No Known Activations