© 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. 21345
    Prev
    Next
    INDEX
    Explanations

    separators followed by words

    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
    åıijå¸ĥåħ¬åijĬ称
    -0.06
     опеÑĢ
    -0.06
     inklus
    -0.05
    brig
    -0.05
    ophilia
    -0.05
    öl
    -0.05
     solitary
    -0.05
     pél
    -0.05
    æľºæ¢°åĪ¶éĢłæľīéĻIJåħ¬åı¸
    -0.05
     INCIDENT
    -0.05
    POSITIVE LOGITS
    izas
    0.06
    anus
    0.05
    çĭ¬åĪĽ
    0.05
     WhatsApp
    0.05
    STM
    0.05
    åĮĸæĪIJ
    0.05
    antal
    0.05
    lish
    0.05
    erja
    0.05
    igy
    0.05
    Activations Density 0.026%

    No Known Activations