© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19804
    Prev
    Next
    INDEX
    Explanations

    and followed by verb

    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
     grounding
    -0.07
    oken
    -0.06
    éĩĩ访æĹ¶è¡¨ç¤º
    -0.06
    Ø°Ùī
    -0.06
    yanto
    -0.06
    तà¥Ģ
    -0.06
    ниÑĨÑĮ
    -0.06
    ult
    -0.06
    ties
    -0.06
    ูà¹Ī
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯ä¸Ģ个
    0.05
     &
    0.05
     e
    0.05
     fav
    0.05
    å¦Ĥæŀľä½ł
    0.05
    æī¾ä¸Ģ个
    0.05
     frag
    0.05
    使çĶ¨åĴĮ
    0.05
    éĢīæĭ©ä¸Ģ个
    0.05
     fac
    0.05
    Activations Density 0.058%

    No Known Activations