© 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. 22224
    Prev
    Next
    INDEX
    Explanations

    is [adjective/noun phrase]

    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
     ben
    -0.05
    -bed
    -0.05
    §
    -0.05
    窦
    -0.05
    ãģĤãĤĮ
    -0.05
    ipot
    -0.04
    ieu
    -0.04
     "
    -0.04
     esper
    -0.04
     пода
    -0.04
    POSITIVE LOGITS
    [âĢ¦
    0.07
     ÐĶека
    0.07
    rea
    0.07
    ÑĪила
    0.06
    полÑĥ
    0.06
     اÙĦÙħاض
    0.06
    alos
    0.06
     auseinander
    0.06
     seguint
    0.06
    >('
    0.06
    Activations Density 0.009%

    No Known Activations