© 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. 19074
    Prev
    Next
    INDEX
    Explanations

    topic and list references

    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
    åħ³æ³¨æĪij们
    -0.06
     confir
    -0.06
    rak
    -0.06
    аÑģÑĤ
    -0.06
    oud
    -0.05
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.05
    漿
    -0.05
     Cop
    -0.05
    abaya
    -0.05
    ayah
    -0.05
    POSITIVE LOGITS
     claims
    0.05
    å¼Ĥ常
    0.05
    éĶĢ
    0.05
    motiv
    0.05
    å®ŀ
    0.05
    ·
    0.05
    جع
    0.05
    vast
    0.05
    åĪĺæĸĩ
    0.05
     billed
    0.05
    Activations Density 0.004%

    No Known Activations