© 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. 17970
    Prev
    Next
    INDEX
    Explanations

    of, in, for, into, against

    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
    orna
    -0.06
    жд
    -0.05
    å§ĭ建äºİ
    -0.05
    สัà¸Ļ
    -0.05
    ("(%
    -0.05
     ...\
    -0.05
    (mapStateToProps
    -0.05
    vere
    -0.05
    é
    -0.05
    ovens
    -0.05
    POSITIVE LOGITS
    ness
    0.06
    ACL
    0.05
    èĩªå¾Ĺ
    0.05
    l
    0.05
    b
    0.05
     afer
    0.05
    檻
    0.05
    ation
    0.05
    adrž
    0.05
    æ§Ľ
    0.05
    Activations Density 0.037%

    No Known Activations