© 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. 20379
    Prev
    Next
    INDEX
    Explanations

    systemic, structural, problems

    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
    áŁģ
    -0.05
    å±ı
    -0.05
    ject
    -0.05
    acu
    -0.05
    .JsonIgnore
    -0.05
    æĬ¢åħĪ
    -0.05
    oot
    -0.05
    æĹ
    -0.05
     sense
    -0.05
    Sense
    -0.05
    POSITIVE LOGITS
    ä½ĵåĪ¶
    0.06
     chan
    0.06
    institution
    0.06
    uson
    0.06
     رأ
    0.06
    uve
    0.06
    виÑģ
    0.06
     Jenner
    0.06
    ching
    0.06
    éĽ¨æ°´
    0.05
    Activations Density 0.018%

    No Known Activations