© 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. 1190
    Prev
    Next
    INDEX
    Explanations

    directional or reciprocal actions

    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
    FU
    -0.23
    åİļ
    -0.23
     sectional
    -0.23
    <dyn
    -0.23
     cliff
    -0.22
    çĿ¡
    -0.21
     Corner
    -0.21
    æĶ»çķ¥
    -0.21
     lying
    -0.21
     clustered
    -0.21
    POSITIVE LOGITS
    åıĮåIJij
    0.45
     обÑĢаÑĤ
    0.41
    åıįä¹ĭ
    0.39
    _reverse
    0.39
    åıįè¿ĩæĿ¥
    0.38
    交æį¢
    0.38
    æĿ¥åĽŀ
    0.38
    åıįé¦Ī
    0.36
     exchange
    0.36
    reverse
    0.35
    Activations Density 0.293%

    No Known Activations