© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2332
    Prev
    Next
    INDEX
    Explanations

    copyright notices, rust code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    KeyPressed
    -0.25
     keyPressed
    -0.25
    jdbc
    -0.24
    _TestCase
    -0.24
    åī¯
    -0.23
    å®ŀéĻħ
    -0.23
    .avi
    -0.23
     Angeles
    -0.23
    ке
    -0.23
    setVisible
    -0.22
    POSITIVE LOGITS
     rust
    0.40
    (crate
    0.35
    rust
    0.34
     Rust
    0.33
     crate
    0.29
    crate
    0.28
    ((&
    0.28
     serde
    0.27
     crates
    0.26
    ffi
    0.25
    Activations Density 0.255%

    No Known Activations