© 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. 1723
    Prev
    Next
    INDEX
    Explanations

    share or like this

    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
    ä¿Ĥ
    -0.23
    suming
    -0.23
     treasurer
    -0.22
    ty
    -0.21
    åħĭåĪ¶
    -0.21
    临
    -0.21
    Mgr
    -0.21
    殿ä¸ĭ
    -0.21
    ($(
    -0.21
    PLIED
    -0.21
    POSITIVE LOGITS
    uin
    0.27
    ãĥªãĥ³ãĤ¯
    0.25
    eln
    0.24
     Grave
    0.24
    rzy
    0.23
    åĩłä¹İ没æľī
    0.23
    nesc
    0.23
    .wik
    0.22
     Tin
    0.22
     recent
    0.21
    Activations Density 0.001%

    No Known Activations