© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    text revision

    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
    è§ģè¯Ĩ
    -0.23
     lẽ
    -0.22
    rowing
    -0.22
    å®ŀè´¨
    -0.21
    æĥ³åĬŀæ³ķ
    -0.19
    thing
    -0.19
    æī§çĿĢ
    -0.19
    stå
    -0.18
    vement
    -0.18
    istration
    -0.18
    POSITIVE LOGITS
    uality
    0.33
    ual
    0.31
    uring
    0.30
    ually
    0.28
    ured
    0.27
    imony
    0.26
    mate
    0.26
    osterone
    0.25
    books
    0.24
    MeshPro
    0.24
    Activations Density 0.073%

    No Known Activations