© 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. 18-TRANSCODER-HP
    7. 88729
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩįä¸Ń
    -0.28
    .onreadystatechange
    -0.28
    ç½ijåıĭè¯Ħ论
    -0.28
    åĺ´
    -0.26
    ombre
    -0.26
    OnUiThread
    -0.24
    atham
    -0.24
     Kahn
    -0.24
    ÑĮÑİ
    -0.23
    룩
    -0.23
    POSITIVE LOGITS
    满
    0.26
    cul
    0.25
     inconvenient
    0.25
    igli
    0.24
     revision
    0.24
    !\
    0.24
    _revision
    0.24
    etur
    0.23
     devise
    0.23
    iner
    0.23
    Activations Density 11.942%

    No Known Activations