© 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. 18478
    Prev
    Next
    INDEX
    Explanations

    can-I

    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
    clam
    -0.06
    truc
    -0.06
    aret
    -0.06
    !’
    -0.06
    ãĤ¨ãĤ¤
    -0.06
     пÑĢиÑĩ
    -0.06
    ëħ¼
    -0.06
    è§ģå¾Ĺ
    -0.06
     Cual
    -0.06
     Geek
    -0.06
    POSITIVE LOGITS
    B
    0.06
     B
    0.06
    umo
    0.06
    ivity
    0.05
    "
    0.05
     Hall
    0.05
    inger
    0.05
     cara
    0.05
     hind
    0.05
    K
    0.05
    Activations Density 0.023%

    No Known Activations