© 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. 39889
    Prev
    Next
    INDEX
    Explanations

    technical/error messages

    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
    Ĥ¬
    -0.33
    {*
    -0.27
    ró
    -0.26
    edBy
    -0.24
    urf
    -0.24
    ä¸įæŃ»
    -0.24
    acob
    -0.24
    letcher
    -0.24
     Robotics
    -0.24
    >{$
    -0.23
    POSITIVE LOGITS
    itlement
    0.29
    linked
    0.27
    à¹Ħà¸Ĥ
    0.25
     dreamed
    0.25
    梦è§ģ
    0.24
     Gran
    0.24
    hesion
    0.24
    Opp
    0.24
    èµ·é£ŀ
    0.24
    置身
    0.24
    Activations Density 0.528%

    No Known Activations