© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    grep command followed by arguments

    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
     passes
    -0.24
    alu
    -0.23
    att
    -0.23
    erk
    -0.23
    åīij
    -0.23
    er
    -0.22
     pass
    -0.22
    HIR
    -0.21
     att
    -0.21
    åĬį
    -0.21
    POSITIVE LOGITS
    广åijĬæľįåĬ¡
    0.24
    ä»ħ代表
    0.23
    éĢłçº¸
    0.23
    æĭħä»»
    0.22
    为ä¸Ńå¿ĥ
    0.22
     Ortiz
    0.21
    @stop
    0.21
     organising
    0.21
    _areas
    0.21
    åħ¨éĿ¢å»ºæĪIJ
    0.21
    Activations Density 0.006%

    No Known Activations