© 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. 18256
    Prev
    Next
    INDEX
    Explanations

    adding or transitioning information

    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
    bacher
    -0.07
    禹
    -0.07
     ukr
    -0.06
    quist
    -0.06
    è§Ħç«ł
    -0.06
    íĽ¨
    -0.06
    å½ĵå½ĵ
    -0.06
    è®°å¾Ĺ
    -0.06
    Bomb
    -0.06
    ipher
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ńæľī
    0.05
    åıªè¦ģä½ł
    0.05
    ais
    0.05
    ÙĩÙĨ
    0.05
    S
    0.05
    çĦ¶å¤§
    0.04
    ons
    0.04
     struct
    0.04
    è°ĵ
    0.04
    è¦ģä½ł
    0.04
    Activations Density 0.130%

    No Known Activations