© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12199
    Prev
    Next
    INDEX
    Explanations

    animals species

    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
    боÑĤ
    -0.22
    åĿĩ使åħ¶
    -0.22
    èIJ½åĪ°å®ŀå¤Ħ
    -0.20
    âīĤ
    -0.20
    pawn
    -0.19
    _ComCallableWrapper
    -0.19
    æĶ¹æŃ£
    -0.19
    æħİéĩį
    -0.19
    åľºåIJĪ
    -0.19
    éľīç´ł
    -0.19
    POSITIVE LOGITS
    ç§įç±»
    0.27
     species
    0.26
    species
    0.25
    åIJįå½ķ
    0.24
     whose
    0.23
    åıĬåħ¶ä»ĸ
    0.21
    ç§į
    0.21
    whose
    0.21
    åĴĮåħ¶ä»ĸ
    0.20
    ë¥ĺ
    0.20
    Activations Density 0.175%

    No Known Activations