© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    announcement or decision

    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
     wait
    -0.21
    èĽī
    -0.21
     -
    -0.21
     suites
    -0.21
    åĪ¶è®¢
    -0.21
    çĽijæĬ¤
    -0.21
    -rise
    -0.21
    Impl
    -0.21
     obviously
    -0.21
    ä½İä¸ĭ
    -0.20
    POSITIVE LOGITS
     nutshell
    0.34
    çĭ¬å®¶
    0.25
    ippet
    0.24
    åĨĻéģĵ
    0.23
    è°ĪåĪ°
    0.23
     desperation
    0.23
    åħ¬å¼Ģ
    0.23
     guise
    0.23
    èĩªåĬ©
    0.23
    mue
    0.23
    Activations Density 0.186%

    No Known Activations