© 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. 21656
    Prev
    Next
    INDEX
    Explanations

    alarms, warning sounds, signaling

    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
     pojed
    -0.06
     besl
    -0.06
    jax
    -0.06
     asiat
    -0.06
    ject
    -0.06
    ICY
    -0.06
    çĻ¾ç§ijåħ¨ä¹¦
    -0.05
    iguez
    -0.05
    llib
    -0.05
     esi
    -0.05
    POSITIVE LOGITS
    走失
    0.06
    è
    0.05
    bler
    0.05
    رÙĨ
    0.05
     Encode
    0.05
    ä¸İä¼ļ
    0.05
    ض
    0.05
    æ±Ĥæķij
    0.05
     anomal
    0.05
    å°Ĩèĩªå·±çļĦ
    0.05
    Activations Density 0.012%

    No Known Activations