© 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. 1000
    Prev
    Next
    INDEX
    Explanations

    use, space, or default values

    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
    PropTypes
    -0.23
     Biggest
    -0.23
    åĨĻéģĵ
    -0.21
     Att
    -0.21
    plaintext
    -0.21
     Ideal
    -0.21
     alex
    -0.21
     пÑĢиÑıÑĤн
    -0.20
     Energ
    -0.20
    andr
    -0.20
    POSITIVE LOGITS
     via
    0.27
    åħ¬åħ±æľįåĬ¡
    0.24
    less
    0.24
     anyway
    0.24
    -independent
    0.23
    -ending
    0.23
     independ
    0.23
    åį³æŶåıijçĶŁ
    0.23
    -less
    0.22
    via
    0.22
    Activations Density 0.171%

    No Known Activations