© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    locations and specific details

    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
    以ä¸ĬçļĦ
    -0.27
    æĬĬè¿ĻäºĽ
    -0.26
    ixo
    -0.24
    —to
    -0.23
    cla
    -0.22
    acks
    -0.22
    æĬĬèĩªå·±
    -0.22
    å°±æĬĬ
    -0.22
    quake
    -0.22
     occup
    -0.21
    POSITIVE LOGITS
     slideshow
    0.23
     Fresh
    0.23
     excerpt
    0.22
     Bare
    0.22
     cabel
    0.21
    Fresh
    0.21
     Threads
    0.21
     ['',
    0.21
    ãĤ§
    0.21
     Counsel
    0.20
    Activations Density 0.079%

    No Known Activations