© 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. 18114
    Prev
    Next
    INDEX
    Explanations

    list name:get bool

    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
    ILT
    -0.06
    gom
    -0.06
    ega
    -0.06
    ëĵł
    -0.06
     обÑĢаÑĤ
    -0.06
    abora
    -0.06
    kra
    -0.06
    pai
    -0.06
     burge
    -0.06
    è¿Ļ款车
    -0.06
    POSITIVE LOGITS
     inters
    0.06
    çĶľ
    0.06
    éĹ´
    0.05
    æľ¬èº«
    0.05
    keit
    0.05
     fin
    0.05
     itself
    0.05
    åĸľ
    0.05
    ains
    0.05
    åĪ°æīĭ
    0.05
    Activations Density 0.001%

    No Known Activations