© 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. 19-TRANSCODER-HP
    7. 8593
    Prev
    Next
    INDEX
    Explanations

    ~

    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
    astes
    -0.29
    èĩªçĦ¶èĢĮ
    -0.28
    .lv
    -0.28
    uencia
    -0.27
    ivism
    -0.27
    ä¼ļéķ¿
    -0.26
    çİĩ
    -0.25
    getContext
    -0.24
    äºĮ代
    -0.24
    ä¸į代表
    -0.24
    POSITIVE LOGITS
    麻çĥ¦
    0.30
     mount
    0.27
    section
    0.27
    stand
    0.25
     central
    0.25
    åĵij
    0.24
     mounts
    0.24
    allen
    0.24
     zenith
    0.24
     shift
    0.24
    Activations Density 0.292%

    No Known Activations