© 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. 842
    Prev
    Next
    INDEX
    Explanations

    material components release changes products individuals groups

    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
    Svg
    -0.23
    çĭĢ
    -0.22
    dex
    -0.21
    以人为
    -0.20
    /pdf
    -0.20
    acies
    -0.20
    .Throw
    -0.20
    scal
    -0.20
     nya
    -0.20
     гÑĢ
    -0.20
    POSITIVE LOGITS
    eks
    0.23
    —including
    0.23
    yll
    0.23
    åĮħæĭ¬
    0.23
     including
    0.22
     Hend
    0.22
    çĶ¨é¤IJ
    0.22
    hel
    0.22
    hear
    0.21
    åıijå±ķæĪĺçķ¥
    0.21
    Activations Density 1.053%

    No Known Activations