© 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. 2482
    Prev
    Next
    INDEX
    Explanations

    video game platforms

    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
    olean
    -0.24
    _phys
    -0.24
     situación
    -0.24
    orate
    -0.23
    identification
    -0.23
    abcdefgh
    -0.22
    _BG
    -0.22
    ä¸ĢåĢĭ人
    -0.21
    attered
    -0.21
    çĽĸ
    -0.21
    POSITIVE LOGITS
    å¹³åı°
    0.37
    å¹³åı°ä¸Ĭ
    0.35
     platform
    0.34
     platforms
    0.34
    çīĪæľ¬
    0.34
     version
    0.30
    æľºåŀĭ
    0.30
    -platform
    0.30
     versions
    0.29
     debut
    0.29
    Activations Density 0.057%

    No Known Activations