© 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. 39180
    Prev
    Next
    INDEX
    Explanations

    position or 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
    ç¼ī
    -0.11
    icum
    -0.10
    åĬŀæ³ķ
    -0.10
    ç½ijéĢļ
    -0.10
    éĵ²
    -0.09
    Ñģел
    -0.09
    edis
    -0.09
    æ±Ĺæ°´
    -0.09
    jack
    -0.09
    èĮĨ
    -0.08
    POSITIVE LOGITS
     position
    0.17
    ä½įç½®
    0.15
    position
    0.15
    çļĦä½įç½®
    0.15
    çļĦåľ°ä½į
    0.14
    (position
    0.14
    -position
    0.14
    Position
    0.14
     Position
    0.14
    åľ°ä½į
    0.14
    Activations Density 0.054%

    No Known Activations