© 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. 17855
    Prev
    Next
    INDEX
    Explanations

    bytes length size

    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
    fil
    -0.05
     rud
    -0.05
     detail
    -0.05
    åħ¶çī¹å¾ģåľ¨äºİ
    -0.05
    sim
    -0.05
    éĹ
    -0.05
    åįģåħŃæĿ¡
    -0.05
    _simulation
    -0.05
     sim
    -0.05
    éĿ¢åIJij
    -0.05
    POSITIVE LOGITS
     quedado
    0.06
    unes
    0.06
    è¿IJæ°Ķ
    0.06
    nus
    0.05
    promise
    0.05
    è¯ģçļĦ
    0.05
    ίÏĥ
    0.05
    лана
    0.05
    åĢ©
    0.05
    ünd
    0.05
    Activations Density 0.014%

    No Known Activations