© 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. 4319
    Prev
    Next
    INDEX
    Explanations

    fossil record

    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
    éĢī举
    -0.10
    èı²
    -0.10
    åĮĿ
    -0.09
    èĮ¸
    -0.08
    é£İå°ļ
    -0.08
    aldi
    -0.08
    èī
    -0.08
    é£İæ°Ķ
    -0.08
    红线
    -0.08
    arda
    -0.08
    POSITIVE LOGITS
    åĮĸçŁ³
    0.14
     fossil
    0.11
     fossils
    0.11
    éģĹ
    0.10
    çŁ³åĮĸ
    0.10
     Pale
    0.10
     formations
    0.10
     Formation
    0.10
    ossil
    0.10
     Lesb
    0.09
    Activations Density 0.077%

    No Known Activations