© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6936
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cú
    -0.28
    esser
    -0.28
    nis
    -0.27
    tur
    -0.27
    tas
    -0.26
    Ĥ¬
    -0.25
    éĺ´éĺ³
    -0.25
    mó
    -0.24
    relationship
    -0.24
    ayas
    -0.24
    POSITIVE LOGITS
    Indented
    0.33
    à¹Ģยà¸Ńะ
    0.25
    ombok
    0.25
    LOTS
    0.25
    FormData
    0.25
    åĨįæĿ¥
    0.25
    åĨ¶
    0.25
    wrap
    0.24
     HANDLE
    0.24
    аÑĨиÑı
    0.23
    Activations Density 0.074%

    No Known Activations