© 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. 21828
    Prev
    Next
    INDEX
    Explanations

    Dental Logistic outcome

    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
    uien
    -0.06
    bum
    -0.05
    voorbeeld
    -0.05
    åĢįçļĦ
    -0.05
     ro
    -0.05
     pewno
    -0.05
    ÐĶÐĶ
    -0.05
    ะ
    -0.05
    наÑĤ
    -0.05
    ам
    -0.05
    POSITIVE LOGITS
    çļĦè¿ĺæĺ¯
    0.07
     Asli
    0.06
    Rép
    0.06
    èĩ³å°ij
    0.05
    onor
    0.05
    lesi
    0.05
    rollable
    0.05
    æľīäºĽåľ°æĸ¹
    0.05
    waÄĩ
    0.05
    åįĩ
    0.05
    Activations Density 0.001%

    No Known Activations