© 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. 51404
    Prev
    Next
    INDEX
    Explanations

    in the first place

    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
    PropertyParams
    -0.10
    _SITE
    -0.10
    wed
    -0.10
    CallableWrapper
    -0.09
    ä¸Ģ缴åĪ°
    -0.09
    .called
    -0.09
    糧
    -0.09
    çİ°éĩijæµģ
    -0.09
    _site
    -0.09
    ziel
    -0.09
    POSITIVE LOGITS
    ãģĿãĤĤãģĿãĤĤ
    0.10
    究竣
    0.09
    èµĸ以
    0.09
    pu
    0.08
    åħĪ
    0.08
    åħ³æ³¨
    0.08
    éĢı
    0.08
    峪
    0.08
    头ä¸Ĭ
    0.08
     cease
    0.08
    Activations Density 0.013%

    No Known Activations