© 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. 2920
    Prev
    Next
    INDEX
    Explanations

    fuel systems and components

    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
    elt
    -0.20
    illing
    -0.19
    ernals
    -0.18
    UAL
    -0.18
    uffer
    -0.18
    yle
    -0.18
    estic
    -0.18
     tuá»ķi
    -0.18
    å¨ī
    -0.18
    ills
    -0.17
    POSITIVE LOGITS
    onom
    0.29
    less
    0.27
    -saving
    0.24
    cent
    0.22
    rats
    0.22
    led
    0.21
    itarian
    0.21
    smith
    0.20
    ing
    0.20
    coni
    0.20
    Activations Density 0.009%

    No Known Activations