© 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. 17214
    Prev
    Next
    INDEX
    Explanations

    type information

    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
    pit
    -0.06
    éľĸ
    -0.06
     absol
    -0.06
    UTA
    -0.06
    ente
    -0.06
    è¦Ĩ
    -0.06
    uta
    -0.06
    æĶ¶å®ĺ
    -0.06
    orius
    -0.06
    louv
    -0.06
    POSITIVE LOGITS
     tre
    0.06
    鼶è·Ŀ离
    0.05
    ver
    0.05
    veg
    0.05
    viet
    0.05
    verst
    0.04
    å½Ĵ
    0.04
     rall
    0.04
    ege
    0.04
    attan
    0.04
    Activations Density 0.224%

    No Known Activations