© 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. 31421
    Prev
    Next
    INDEX
    Explanations

    Rust programming language syntax

    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
    æįķæįī
    -0.10
     Narr
    -0.09
    导åIJij
    -0.09
    æµ®åĬ¨
    -0.09
    é©´
    -0.09
    宿
    -0.09
    mys
    -0.09
    enh
    -0.08
    çī¹éķ¿
    -0.08
    å±IJ
    -0.08
    POSITIVE LOGITS
     Rust
    0.12
    rust
    0.11
    éĶĪ
    0.11
     rust
    0.11
    éĵģ
    0.11
    fmt
    0.10
    serde
    0.10
     serde
    0.10
    å®īå®ģ
    0.10
    <()>
    0.10
    Activations Density 0.695%

    No Known Activations