© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19702
    Prev
    Next
    INDEX
    Explanations

    gem install

    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
    owed
    -0.06
    izabeth
    -0.06
    owing
    -0.06
    èĤºèħij
    -0.05
    ä¸įè´Ł
    -0.05
    ìħĶìķ¼
    -0.05
    REP
    -0.05
    ows
    -0.05
     Peninsula
    -0.05
    èĪī
    -0.05
    POSITIVE LOGITS
    ĵĴ
    0.05
    yal
    0.05
     memes
    0.05
    esta
    0.05
    iglia
    0.05
    å®Įç»ĵ
    0.05
    åĪ©äºļ
    0.05
    hte
    0.05
    soles
    0.05
     pa
    0.05
    Activations Density 0.047%

    No Known Activations