© 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. 57987
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    roids
    -0.29
    ï¼ĮãĢĬ
    -0.28
     cargo
    -0.26
    座ä½į
    -0.26
     Ring
    -0.25
     sin
    -0.24
     con
    -0.24
    æľ¬ä¹¦
    -0.24
    ager
    -0.23
     among
    -0.23
    POSITIVE LOGITS
    ingham
    0.28
    AttributeName
    0.27
    евиÑĩ
    0.26
    Unauthorized
    0.26
    scratch
    0.25
    åīįæĸ¹
    0.25
     GetComponent
    0.24
    North
    0.24
     Ahead
    0.24
    iffies
    0.24
    Activations Density 0.002%

    No Known Activations