© 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. 20445
    Prev
    Next
    INDEX
    Explanations

    arterial branches

    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
    ered
    -0.06
    审
    -0.06
    го
    -0.05
    holz
    -0.05
    ¾
    -0.05
    èħ«
    -0.05
    IVID
    -0.05
    VO
    -0.05
    ç´ł
    -0.05
    æ»ģå·ŀ
    -0.05
    POSITIVE LOGITS
    ond
    0.07
    ujan
    0.06
    å½Ĵ纳
    0.06
    ubs
    0.06
     rot
    0.05
    isko
    0.05
    è¯łéĩĬ
    0.05
    ars
    0.05
    imetr
    0.05
    iska
    0.05
    Activations Density 0.513%

    No Known Activations