© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16838
    Prev
    Next
    INDEX
    Explanations

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    rys
    -0.24
    åı¦ä¸Ģç§į
    -0.22
    TemplateName
    -0.22
    æľīç§į
    -0.21
    第äºĮç§į
    -0.21
    æŁIJç§į
    -0.21
    _LP
    -0.19
    uish
    -0.19
    CHANT
    -0.19
    åħ·
    -0.19
    POSITIVE LOGITS
    诸å¦Ĥ
    0.37
    å¦Ĥ
    0.29
     like
    0.29
    æ¯Ķå¦Ĥ
    0.28
    such
    0.28
    ä¾ĭå¦Ĥ
    0.28
     such
    0.28
     likes
    0.27
     nhÆ°
    0.26
    èѬå¦Ĥ
    0.26
    Activations Density 0.098%

    No Known Activations