© 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. 9-TRANSCODER-HP
    7. 29873
    Prev
    Next
    INDEX
    Explanations

    ace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ós
    -0.27
    åIJ¬
    -0.26
    æĶ¯
    -0.26
    绣
    -0.25
     donor
    -0.25
     motivate
    -0.25
    -flat
    -0.25
    enth
    -0.24
    .sp
    -0.24
    Enable
    -0.24
    POSITIVE LOGITS
    åĬŁ
    0.28
    åī¯ä¼ļéķ¿
    0.26
    éĢĢåĩº
    0.26
    产éĶĢ
    0.26
    ogany
    0.24
    寡
    0.24
    bler
    0.24
    aeda
    0.23
    arella
    0.23
    大ä¼Ĺ
    0.23
    Activations Density 5.192%

    No Known Activations