© 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. 20387
    Prev
    Next
    INDEX
    Explanations

    choose use select buy

    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
    çĪĨ
    -0.06
     {}:
    -0.06
    å¾Ĺèµ·
    -0.06
    ushed
    -0.06
    /preferences
    -0.06
    usher
    -0.06
    acher
    -0.06
    theless
    -0.06
    ocked
    -0.06
    specialchars
    -0.06
    POSITIVE LOGITS
    ä»ĸæīĢ
    0.06
     BOOT
    0.05
    ering
    0.05
    boot
    0.05
    este
    0.05
     foll
    0.05
    tam
    0.05
    çĽ¸å¯¹åºĶçļĦ
    0.05
    em
    0.05
    åħ¶æīĢ
    0.05
    Activations Density 0.003%

    No Known Activations