© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    all-wheel drive

    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
    ä¸İåıijå±ķ
    -0.27
    åĴĮåıijå±ķ
    -0.24
    ses
    -0.24
     penis
    -0.23
     DM
    -0.23
    驹
    -0.23
    ä¸įåĩºæĿ¥
    -0.23
     linker
    -0.23
     jelly
    -0.22
    ä¸įæľį
    -0.22
    POSITIVE LOGITS
    å±Ĥ
    0.25
    è§Ĩè§Ĵ
    0.23
    ately
    0.23
    èµĭ
    0.23
    ment
    0.23
    ¦
    0.23
    _subs
    0.23
    ExceptionHandler
    0.22
    åijĺ
    0.22
    ige
    0.22
    Activations Density 0.007%

    No Known Activations