© 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. 21785
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude

    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
    ấp
    -0.07
    новÑĢемен
    -0.06
    abol
    -0.06
     brows
    -0.06
    ateria
    -0.06
    ierta
    -0.06
    akta
    -0.06
    avia
    -0.06
     Dimensioni
    -0.06
    è¿Ļ两款
    -0.06
    POSITIVE LOGITS
    alam
    0.05
    éĿ¢åīį
    0.05
    jang
    0.05
     streak
    0.05
     He
    0.05
    rys
    0.05
    He
    0.05
    å®ŀéĻħ
    0.05
    ram
    0.05
    åĥıæĺ¯
    0.05
    Activations Density 0.005%

    No Known Activations