© 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. 18916
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     Ro
    -0.05
    orto
    -0.05
    åIJĦè¡Į
    -0.05
    ago
    -0.05
    åīįèĢħ
    -0.05
    ÑĢо
    -0.05
     занÑı
    -0.05
    _ro
    -0.05
     occupa
    -0.05
    ahah
    -0.05
    POSITIVE LOGITS
    czyk
    0.07
    å¤©åľ°éĹ´
    0.06
    hb
    0.06
    åĻ¬
    0.05
    iov
    0.05
    rzy
    0.05
     kult
    0.05
     dispens
    0.05
    Shock
    0.05
    ä¼łäºº
    0.05
    Activations Density 0.119%

    No Known Activations