© 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. 887
    Prev
    Next
    INDEX
    Explanations

    MacBook Pro

    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
    积æŀģä½ľçĶ¨
    -0.25
    NonNull
    -0.25
    çĶº
    -0.23
    edList
    -0.23
    eah
    -0.22
    à¸Ńà¸ĩ
    -0.22
    ledo
    -0.22
    eds
    -0.21
    uele
    -0.21
    Duplicates
    -0.21
    POSITIVE LOGITS
    -ish
    0.26
    iful
    0.23
    v
    0.22
     scalp
    0.21
    IMUM
    0.21
     Mk
    0.20
    /DD
    0.20
    åijķ
    0.20
     SAME
    0.19
    ä¸Ģä¸ĸ
    0.19
    Activations Density 0.006%

    No Known Activations