© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8128
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸı
    -0.29
    åŃ°
    -0.29
     Marin
    -0.26
    ")+
    -0.25
    幸ç¦ıæĦŁ
    -0.25
    ä¸ĢåĪĨéĴŁ
    -0.25
    éĻĽ
    -0.25
    æĺ¯ä»Ģä¹Īåij¢
    -0.24
    )\↵
    -0.24
    profits
    -0.24
    POSITIVE LOGITS
     possible
    0.86
    possible
    0.77
     Possible
    0.68
     posible
    0.65
    Possible
    0.60
     possibile
    0.58
    _possible
    0.54
     possÃŃvel
    0.54
     impossible
    0.50
     necessary
    0.46
    Activations Density 0.141%

    No Known Activations