© 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. 2394
    Prev
    Next
    INDEX
    Explanations

    beginning, during, move, stops

    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
    	TokenName
    -0.28
    InputBorder
    -0.27
    =pk
    -0.26
    :absolute
    -0.26
    =query
    -0.24
    .hm
    -0.24
    _EOL
    -0.24
    _FRONT
    -0.24
    ,module
    -0.23
    _Anim
    -0.23
    POSITIVE LOGITS
    ÑĩÑĢежден
    0.25
    leg
    0.24
    梽
    0.24
    æĦŁåħ´è¶£
    0.24
    æľĹ
    0.24
     Rom
    0.23
    éķ´
    0.23
    åĢį
    0.23
    ÓĽ
    0.23
    è°ĭ
    0.23
    Activations Density 0.162%

    No Known Activations