© 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. 57347
    Prev
    Next
    INDEX
    Explanations

    space exploration

    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
    europ
    -0.32
     Destruction
    -0.28
    ä¸įèĥ½ä¸ºç©º
    -0.26
    storeId
    -0.26
     lifetime
    -0.25
    lifetime
    -0.25
    Dur
    -0.24
     terra
    -0.24
    agnar
    -0.24
    versible
    -0.24
    POSITIVE LOGITS
     pillow
    0.26
     alt
    0.26
    æ¸ħæĺİ
    0.26
     altitude
    0.25
    ì¹Ļ
    0.25
     viet
    0.25
    mers
    0.25
    QQ
    0.25
     sheet
    0.24
    æ¨Ł
    0.24
    Activations Density 0.001%

    No Known Activations