© 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. 23870
    Prev
    Next
    INDEX
    Explanations

    enables something to happen

    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
    yna
    -0.11
    ening
    -0.10
    ince
    -0.09
    åĵĩ
    -0.09
    为äºĨéģ¿åħį
    -0.09
    è¯Ĵ
    -0.09
    cheme
    -0.09
    eld
    -0.08
    iled
    -0.08
    çīµæĮĤ
    -0.08
    POSITIVE LOGITS
    /disable
    0.15
    ment
    0.12
    -bodied
    0.11
     dÃłng
    0.11
    LING
    0.10
    说æľį
    0.09
    urator
    0.09
    ìĤ¬íķŃ
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    ities
    0.09
    Activations Density 0.020%

    No Known Activations