© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 380
    Prev
    Next
    INDEX
    Explanations

    route planning, description, or related to paths

    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
     routine
    -0.23
    eral
    -0.21
     viá»ĩc
    -0.20
     rud
    -0.19
    orable
    -0.19
     Routine
    -0.19
    neath
    -0.19
    ç«Ń
    -0.18
     cosa
    -0.18
    roe
    -0.18
    POSITIVE LOGITS
    geist
    0.23
    /path
    0.22
    books
    0.22
    /place
    0.22
    finder
    0.21
    ophys
    0.20
    ability
    0.20
     иÑģп
    0.19
    llib
    0.19
     пиÑĤаниÑı
    0.19
    Activations Density 0.023%

    No Known Activations