© 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. 19728
    Prev
    Next
    INDEX
    Explanations

    kickoff or start time

    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
    .idea
    -0.09
     Äijá»ĵ
    -0.09
    PK
    -0.08
    åİ»äºĨ
    -0.08
    é«ĺéĢŁ
    -0.08
    SetActive
    -0.08
    nger
    -0.08
    åİ»åģļ
    -0.08
    ifar
    -0.08
     Gamer
    -0.08
    POSITIVE LOGITS
    æijĦ
    0.09
    å®ļå±ħ
    0.09
    帷
    0.08
    ãĤĴè¿İ
    0.08
     postponed
    0.08
    åŀ¦
    0.08
    hsi
    0.08
    SED
    0.08
    ãģ¤ãģį
    0.08
    ä»·
    0.08
    Activations Density 0.016%

    No Known Activations