© 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. 39826
    Prev
    Next
    INDEX
    Explanations

    child

    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
    ¢åįķ
    -0.29
     organ
    -0.29
     ($)
    -0.28
    -0.26
    -rad
    -0.25
     succeeding
    -0.25
    ä¸IJ
    -0.24
    ammer
    -0.24
     Äijâu
    -0.24
    idan
    -0.24
    POSITIVE LOGITS
     trait
    0.28
    æľºæ¢°åĮĸ
    0.28
    å°Ħ
    0.27
    èĩªå¾ĭ
    0.26
    .transfer
    0.25
     Rue
    0.25
    æķ´æķ´
    0.25
    [--
    0.25
    trait
    0.25
     yyn
    0.24
    Activations Density 0.844%

    No Known Activations