© 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. 1098
    Prev
    Next
    INDEX
    Explanations

    consecutive or straight periods

    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
    -
    -0.25
    bers
    -0.25
    åIJįèªī
    -0.24
     particular
    -0.24
    åİŁæľīçļĦ
    -0.23
     Sp
    -0.23
    ä¹ĭéĹ´
    -0.23
    icum
    -0.23
    ä¹ĭ
    -0.22
    uges
    -0.22
    POSITIVE LOGITS
    OrCreate
    0.25
    éĩįè¦ģåĽłç´ł
    0.25
    tier
    0.22
    hashed
    0.21
    ably
    0.21
    YPE
    0.21
    _acl
    0.20
    梨
    0.20
     Personally
    0.20
    æĬĹæĭĴ
    0.20
    Activations Density 0.009%

    No Known Activations