© 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. 34019
    Prev
    Next
    INDEX
    Explanations

    RPC and web services

    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
    OfSize
    -0.09
     PTR
    -0.08
    èµİ
    -0.08
     Abel
    -0.08
    主
    -0.08
     BUG
    -0.08
    强çĥĪ
    -0.08
     ÑģеÑĢии
    -0.08
    主ä½ĵ
    -0.08
    _MALLOC
    -0.08
    POSITIVE LOGITS
    .rpc
    0.11
    éĻµ
    0.10
    çıIJ
    0.10
    è¿ľç¨ĭ
    0.10
    è¯
    0.10
    åºŁ
    0.10
     thrift
    0.10
    _RPC
    0.10
     gar
    0.09
     remote
    0.09
    Activations Density 0.392%

    No Known Activations