© 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. 17931
    Prev
    Next
    INDEX
    Explanations

    removing prefixes and suffixes

    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
    iot
    -0.07
    åķıåIJĪãģĽ
    -0.07
    iam
    -0.07
    wok
    -0.07
    oke
    -0.07
    iel
    -0.07
    един
    -0.06
    ĵĴ
    -0.06
    ffin
    -0.06
    pin
    -0.06
    POSITIVE LOGITS
    æ²»
    0.06
    èĩªåĪ¶
    0.05
     cur
    0.05
    Ñįй
    0.05
    angan
    0.05
    ä¿®æŃ£
    0.05
    iness
    0.05
    D
    0.05
     adv
    0.05
     catch
    0.05
    Activations Density 0.040%

    No Known Activations