© 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. 2755
    Prev
    Next
    INDEX
    Explanations

    disable

    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
     idea
    -0.25
    å¥Ķ
    -0.24
    è·¯å¾Ħ
    -0.23
     path
    -0.22
    Nike
    -0.22
    ponsor
    -0.21
    çļĦæĥ³æ³ķ
    -0.21
     trib
    -0.21
    æĹłæķ°
    -0.21
    idea
    -0.21
    POSITIVE LOGITS
    elier
    0.22
    istan
    0.22
    inho
    0.21
    ÑĤÑĥÑĢ
    0.21
    landers
    0.21
    ANNOT
    0.21
    çĶŁæ´»è´¨éĩı
    0.20
    åĩłæŃ¥
    0.20
     cooker
    0.20
    uelle
    0.20
    Activations Density 0.001%

    No Known Activations