© 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. 17717
    Prev
    Next
    INDEX
    Explanations

    strategy and plans

    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
     F
    -0.06
    é«ĺåİĭ
    -0.06
     presence
    -0.06
    F
    -0.06
    ä¹ī
    -0.05
     H
    -0.05
     subs
    -0.05
    ä¹īçļĦ
    -0.05
     (
    -0.05
     security
    -0.05
    POSITIVE LOGITS
    çķĮ
    0.07
     revolu
    0.07
    ennie
    0.07
     Stich
    0.06
    +self
    0.06
    lob
    0.06
     Insomma
    0.06
     olabil
    0.06
    illion
    0.06
    åıijå¸ĥä¿¡æģ¯
    0.06
    Activations Density 0.046%

    No Known Activations