© 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. 17158
    Prev
    Next
    INDEX
    Explanations

    We, Certainly, Google, C, Prior, Wild, Gab, All, Ash, Santa

    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
    ÙĪÙĦات
    -0.05
    Ñĩков
    -0.05
    arge
    -0.05
    erne
    -0.05
    troppo
    -0.05
    æ·ĭ
    -0.05
    isted
    -0.05
    again
    -0.05
     comparisons
    -0.05
    ulon
    -0.05
    POSITIVE LOGITS
    room
    0.06
     scram
    0.05
    ä½ľæ³ķ
    0.05
    æĢ§åĬŁèĥ½
    0.05
    æ®·
    0.05
    غÙĨ
    0.05
    infl
    0.05
    á»ħn
    0.05
     Ãľn
    0.05
    crew
    0.05
    Activations Density 0.127%

    No Known Activations