© 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. 708
    Prev
    Next
    INDEX
    Explanations

    in place

    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
     aloud
    -0.28
    sic
    -0.22
     trivia
    -0.20
    åĩºèº«
    -0.20
    Ĥ¨
    -0.20
    plex
    -0.19
    åĢĴåľ¨
    -0.19
    磻
    -0.19
    again
    -0.18
    wear
    -0.18
    POSITIVE LOGITS
    ä¸Ģå¥Ĺ
    0.29
    /disable
    0.29
    /off
    0.25
    å·²ä¹ħçļĦ
    0.24
    enie
    0.23
    iment
    0.22
    ward
    0.22
    æīĢè°ĵ
    0.22
    ilha
    0.21
    /out
    0.21
    Activations Density 0.011%

    No Known Activations