© 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. 517
    Prev
    Next
    INDEX
    Explanations

    collective followed by group concept

    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
    ning
    -0.26
    nt
    -0.22
    pery
    -0.21
    imum
    -0.21
    wards
    -0.20
    sea
    -0.20
    dater
    -0.20
    da
    -0.20
    iest
    -0.20
    å½ĵåľ°çļĦ
    -0.19
    POSITIVE LOGITS
    -minded
    0.25
    ity
    0.24
    éĥ½çŁ¥éģĵ
    0.24
     wisdom
    0.23
     nouns
    0.23
     minded
    0.22
    izador
    0.21
    /team
    0.21
    ìłģìľ¼ë¡ľ
    0.20
     Ñĥзна
    0.20
    Activations Density 0.010%

    No Known Activations