© 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. 530
    Prev
    Next
    INDEX
    Explanations

    bone marrow and blood cells

    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
    gee
    -0.24
    åıłåĬł
    -0.24
    åĽłæŀľ
    -0.23
     causal
    -0.22
     Protective
    -0.21
     acceptable
    -0.21
     зн
    -0.21
     printable
    -0.21
     actionable
    -0.21
     protective
    -0.21
    POSITIVE LOGITS
    æºIJæ³ī
    0.26
    åŁºåľ°
    0.26
     located
    0.26
     prer
    0.25
    ä½įäºİ
    0.25
    æºIJ头
    0.25
    source
    0.25
     centres
    0.24
    æīĢåľ¨åľ°
    0.24
    .modules
    0.24
    Activations Density 0.084%

    No Known Activations