© 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. 20975
    Prev
    Next
    INDEX
    Explanations

    influential

    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
     @
    -0.06
    ods
    -0.06
    aglio
    -0.05
    ogn
    -0.05
    èģĶ
    -0.05
    弦
    -0.05
    ags
    -0.05
    åħ»èĢģ
    -0.05
    olor
    -0.05
    AGING
    -0.05
    POSITIVE LOGITS
    urop
    0.07
     incor
    0.06
    ïn
    0.06
    lement
    0.06
     influential
    0.06
     impart
    0.06
     hó
    0.06
    ment
    0.06
     poll
    0.06
    kir
    0.06
    Activations Density 0.009%

    No Known Activations