© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    Oreo, Android, resource, Order, template

    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
    pine
    -0.31
    ystate
    -0.23
    ijľ
    -0.23
    itto
    -0.23
    éķ¿è¿ľ
    -0.22
    friend
    -0.22
    retry
    -0.21
     weblog
    -0.21
    coverage
    -0.21
    lexical
    -0.21
    POSITIVE LOGITS
    /Framework
    0.24
    åĴ¸
    0.22
     alike
    0.22
    striction
    0.22
    chalk
    0.21
    饺
    0.21
    (___
    0.21
     chalk
    0.21
    å®Įæķ´
    0.21
    å§ĭ
    0.21
    Activations Density 0.001%

    No Known Activations