© 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. 40248
    Prev
    Next
    INDEX
    Explanations

    end-stage disease

    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
     towers
    -0.28
    TreeView
    -0.27
    inke
    -0.27
    “She
    -0.26
    æľĽåİ»
    -0.26
    veillance
    -0.26
    _drvdata
    -0.25
    é»ĺé»ĺåľ°
    -0.25
    _blueprint
    -0.25
    åİŁæłĩé¢ĺ
    -0.25
    POSITIVE LOGITS
    夹
    0.30
    çĨŁæĤī
    0.29
    èģĶéĤ¦
    0.27
     vice
    0.27
     Vice
    0.27
    çIJĨ
    0.26
    auer
    0.26
    tr
    0.26
    prev
    0.25
    shift
    0.25
    Activations Density 0.122%

    No Known Activations