© 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. 764
    Prev
    Next
    INDEX
    Explanations

    Read more

    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
    æķ£
    -0.23
    unte
    -0.23
    *=*=
    -0.23
     pres
    -0.22
    raries
    -0.21
     deadlines
    -0.20
    ushman
    -0.20
     independent
    -0.20
     consolid
    -0.20
    ochond
    -0.20
    POSITIVE LOGITS
    详æĥħ
    0.30
    æŁ¥çľĭ详æĥħ
    0.28
    å±ķå¼Ģ
    0.27
    çŃīçŃī
    0.26
    详è§ģ
    0.25
    åĶ
    0.24
    abbrev
    0.24
    /details
    0.24
    詳ãģĹãģı
    0.23
    wig
    0.23
    Activations Density 0.014%

    No Known Activations