© 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. 21196
    Prev
    Next
    INDEX
    Explanations

    represents the outcome or result

    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
    åijĬ
    -0.06
    å¹´èİ·
    -0.06
    òn
    -0.06
    variably
    -0.06
     cient
    -0.06
    ulled
    -0.06
    ilea
    -0.06
    adol
    -0.06
    illos
    -0.06
    redient
    -0.05
    POSITIVE LOGITS
    able
    0.06
    ish
    0.05
    iy
    0.05
    ç»ĦåIJĪ
    0.05
    èĥľä»»
    0.05
    åIJīå°Ķ
    0.05
    æ··åIJĪ
    0.05
    Äĵ
    0.05
    ables
    0.05
    fac
    0.05
    Activations Density 0.013%

    No Known Activations