© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    audio gain and compression level

    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
    ç®Ĺæ³ķ
    -0.26
     Splash
    -0.25
     Yad
    -0.25
    åłĨæĶ¾
    -0.24
     naw
    -0.24
    .period
    -0.23
    .Container
    -0.23
    (period
    -0.23
     feas
    -0.23
     disag
    -0.23
    POSITIVE LOGITS
     polarity
    0.26
     capacit
    0.25
     whiskey
    0.25
     amplifier
    0.24
     resistor
    0.24
     signal
    0.23
    æıĴ座
    0.23
    presso
    0.23
    é¢Ĩè¡Ķ
    0.23
    ä¿¡åı·
    0.23
    Activations Density 0.019%

    No Known Activations