© 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. 41203
    Prev
    Next
    INDEX
    Explanations

    person

    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
     Wei
    -0.25
    çŃīéĹ®é¢ĺ
    -0.24
    Drupal
    -0.24
     blah
    -0.24
    ByExample
    -0.24
     fertile
    -0.23
    ivicrm
    -0.23
    ç¿Ĵ
    -0.23
    gere
    -0.23
    oland
    -0.23
    POSITIVE LOGITS
    ured
    0.31
    èģĮä¸ļæĬĢæľ¯
    0.29
    ä¿Ŀè¯ģ
    0.28
    <Any
    0.27
    belt
    0.27
    Õ²
    0.27
    çĽĸ
    0.26
    eping
    0.25
    ਪ
    0.24
    å¾Ħ
    0.24
    Activations Density 0.906%

    No Known Activations