© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20209
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
    LEX
    -0.06
    andu
    -0.06
    ired
    -0.06
    chern
    -0.06
    çĶŁæķĪåIJİ
    -0.05
    ilt
    -0.05
    att
    -0.05
    thes
    -0.05
    ellte
    -0.05
     opdracht
    -0.05
    POSITIVE LOGITS
     theirs
    0.07
    èijĹ
    0.06
    agger
    0.06
     scom
    0.06
    _ack
    0.06
    ê°ĢìļĶ
    0.05
    folio
    0.05
    aine
    0.05
     zupeÅĤ
    0.05
    箸
    0.05
    Activations Density 0.009%

    No Known Activations