© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    GPU use

    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
     Surf
    -0.24
    quiz
    -0.23
    å®Ł
    -0.22
    "%
    -0.22
     SPEED
    -0.22
    æĭ¯æķij
    -0.22
     Speed
    -0.21
     Ladies
    -0.21
     Khal
    -0.21
     labelled
    -0.21
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.38
    åĪĻ
    0.35
    åıįèĢĮ
    0.34
    åīĩ
    0.30
    Wars
    0.30
     however
    0.29
    åıįåĢĴ
    0.29
    åı¦æľī
    0.28
     other
    0.27
    idUser
    0.27
    Activations Density 0.169%

    No Known Activations