© 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. 19199
    Prev
    Next
    INDEX
    Explanations

    along the lines of

    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
    ami
    -0.06
     доÑģÑĤ
    -0.06
    èĥ¡
    -0.05
    chy
    -0.05
    iz
    -0.05
    åĪ°å¤©
    -0.05
    ossi
    -0.05
    ä½°
    -0.05
    arend
    -0.05
     diz
    -0.05
    POSITIVE LOGITS
    ÙĨÙĩ
    0.06
    ueux
    0.06
     regress
    0.06
    ä¸ľè¥¿
    0.05
    ENTS
    0.05
    ();)
    0.05
    ëł¹
    0.05
    GORITH
    0.05
     audit
    0.05
    ress
    0.05
    Activations Density 0.070%

    No Known Activations