© 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. 21096
    Prev
    Next
    INDEX
    Explanations

    words following 'for' or 'a'

    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
    zij
    -0.06
    åľĨ
    -0.06
     sparing
    -0.05
    æ¸łéģĵ
    -0.05
     channel
    -0.05
    ÑĤÑĥи
    -0.05
     Aleman
    -0.05
     anterior
    -0.05
    ťaž
    -0.05
    alg
    -0.05
    POSITIVE LOGITS
    burgh
    0.06
    unsch
    0.06
     trouble
    0.06
    endis
    0.06
    ssa
    0.06
    ETR
    0.06
    ç§ijéķ¿
    0.06
    ãĥ³ãĥīãĥ³
    0.06
    INF
    0.05
    ä¸ŃæĮĩåĩº
    0.05
    Activations Density 0.361%

    No Known Activations