© 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. 14-TRANSCODER-HP
    7. 41201
    Prev
    Next
    INDEX
    Explanations

    business and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    榨
    -0.26
    uten
    -0.25
     zw
    -0.25
    çºĤ
    -0.25
     disdain
    -0.25
     forsk
    -0.24
    -fr
    -0.24
    AtPath
    -0.24
     @@
    -0.24
    minated
    -0.24
    POSITIVE LOGITS
    çļĦåľ°
    0.25
    äºĴ缸
    0.25
    phabet
    0.25
    èĭķ
    0.25
     earlier
    0.25
    MLS
    0.25
    lier
    0.24
     næ
    0.24
    ä¸ĢæľŁ
    0.24
    ysters
    0.24
    Activations Density 1.644%

    No Known Activations