© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    contrast ratio and dynamic range

    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
     SUBSTITUTE
    -0.23
     деÑıÑĤелÑĮноÑģÑĤи
    -0.23
    GPS
    -0.23
     Gaut
    -0.23
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    -0.22
    HECK
    -0.22
    罡
    -0.22
    NAL
    -0.22
    _tl
    -0.22
    å¼ķåĬĽ
    -0.21
    POSITIVE LOGITS
     ratio
    0.29
    .closed
    0.28
    -rich
    0.28
     separation
    0.27
     billions
    0.25
     enhanced
    0.25
    å°ģéĹŃ
    0.24
     honor
    0.24
     Ratio
    0.24
     built
    0.24
    Activations Density 0.010%

    No Known Activations