© 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. 2830
    Prev
    Next
    INDEX
    Explanations

    Walt Disney or waltl

    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
    ä¸Ģç³»åĪĹ
    -0.25
    ity
    -0.23
    hape
    -0.20
    FromClass
    -0.20
    ä¸Ģç§į
    -0.20
    ivial
    -0.19
    omination
    -0.19
    индивид
    -0.19
    polate
    -0.19
    ä¸Ģç¯ĩ
    -0.19
    POSITIVE LOGITS
    gether
    0.27
    phan
    0.25
    ers
    0.24
    äºĭä¸ļåıijå±ķ
    0.23
    uate
    0.23
    ify
    0.23
    ï¸ı
    0.22
    ward
    0.22
    ships
    0.22
    soever
    0.22
    Activations Density 0.002%

    No Known Activations