© 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. 3014
    Prev
    Next
    INDEX
    Explanations

    query and its follow-up actions

    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
    yı
    -0.22
    ../../../
    -0.20
    /her
    -0.20
    /or
    -0.19
    ening
    -0.19
    åģ¥åħ¨
    -0.19
    icity
    -0.18
    Ñĩем
    -0.18
    ych
    -0.18
    olest
    -0.18
    POSITIVE LOGITS
    /response
    0.25
    /question
    0.24
    ä¸įæ¸ħ
    0.24
    /command
    0.23
    dsl
    0.23
    stellung
    0.23
    -response
    0.23
    er
    0.23
    ä¸įéĢļ
    0.22
    able
    0.21
    Activations Density 0.059%

    No Known Activations