© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    themed party

    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
    /disable
    -0.27
    fulness
    -0.24
    less
    -0.21
    lessness
    -0.21
    /vnd
    -0.21
    !--
    -0.19
    wright
    -0.19
    ä¸İåıijå±ķ
    -0.19
    çļĦæĥħæĦŁ
    -0.19
    vement
    -0.18
    POSITIVE LOGITS
    tion
    0.20
    isplay
    0.20
    ly
    0.20
    ÃŃcio
    0.19
    lope
    0.19
    ourt
    0.19
     needle
    0.19
    å¤ļãģı
    0.18
    们éĥ½
    0.18
    mini
    0.18
    Activations Density 0.065%

    No Known Activations