© 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. 15866
    Prev
    Next
    INDEX
    Explanations

    author names and dates

    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
     mükem
    -0.31
     Geile
    -0.31
    âīĤ
    -0.26
    numerusform
    -0.26
    isclosed
    -0.26
     saģlıkl
    -0.25
    #ga
    -0.25
    europäische
    -0.25
    á¿ij
    -0.25
     raÄŁ
    -0.25
    POSITIVE LOGITS
    åIJįå½ķ
    0.35
    çī©ç§į
    0.34
    éī´å®ļ
    0.32
    æ£Ģçĸ«
    0.31
    ç¹ģæ®ĸ
    0.31
    éĩİå¤ĸ
    0.31
    æķ°æį®åºĵ
    0.28
    åįļçī©
    0.28
    Species
    0.28
    è®°å½ķ
    0.27
    Activations Density 0.376%

    No Known Activations