© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    ’s prefixes with digits or specific words

    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
    atre
    -0.19
    FPS
    -0.18
    Behaviour
    -0.18
     dra
    -0.18
     effected
    -0.18
     NotImplementedError
    -0.18
    ãģĹãĤĩãģĨ
    -0.18
    ÑģпоÑĢ
    -0.17
    åĹ£
    -0.17
    å½ĵæĹ¥
    -0.17
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.30
    amp
    0.30
    ÂĢÂ
    0.26
    åIJİçļĦ
    0.25
    åĿĢ
    0.25
    onna
    0.25
    们çļĦ
    0.23
    é¾Ħ
    0.23
    lis
    0.23
    ¨
    0.23
    Activations Density 0.016%

    No Known Activations