© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21022
    Prev
    Next
    INDEX
    Explanations

    numbered or coded lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
     pens
    -0.06
    olla
    -0.06
     Olson
    -0.05
    ç»ħ
    -0.05
    åħ¬å¼Ģåıijè¡Į
    -0.05
     pena
    -0.05
    缮çļĦåľ¨äºİ
    -0.05
    openh
    -0.05
    rus
    -0.05
    atelier
    -0.05
    POSITIVE LOGITS
    æĹłåħ³
    0.06
    æĶ¾è¿ĩ
    0.06
    åħĭ森
    0.05
     cÃłng
    0.05
    åĪºæ¿Ģ
    0.05
    æĹ¥åħ¬å¸ĥ
    0.05
    avu
    0.05
     alike
    0.05
    åĬ©
    0.05
     ìĸ´ëĬIJ
    0.05
    Activations Density 0.026%

    No Known Activations