© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    UV-B radiation

    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
     porr
    -0.24
     Orient
    -0.24
    åĭŁèµĦ
    -0.23
    Remaining
    -0.22
     poo
    -0.22
    ENCY
    -0.22
    ä¸Ģæĸ¹
    -0.22
    å°±å¾Ī
    -0.21
    oration
    -0.21
    .nb
    -0.21
    POSITIVE LOGITS
    _CM
    0.24
     ell
    0.23
     osc
    0.22
     Disp
    0.21
    _NAMES
    0.21
     Cookies
    0.20
     Wig
    0.20
     blink
    0.20
    .decorate
    0.20
    ipers
    0.20
    Activations Density 0.001%

    No Known Activations