© 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. 29779
    Prev
    Next
    INDEX
    Explanations

    people

    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
    ERE
    -0.29
    igmatic
    -0.28
    ören
    -0.28
    oss
    -0.27
    çŃ¾
    -0.27
    à´³
    -0.26
    çĨŁ
    -0.26
    ernote
    -0.26
    çĬ¯ç½ªå«Įçĸij
    -0.26
    ба
    -0.26
    POSITIVE LOGITS
    Scaler
    0.32
     electro
    0.26
    æī¾åĽŀ
    0.26
    mission
    0.24
    [next
    0.24
    apia
    0.24
    éĶŁ
    0.24
    åİ»æİī
    0.24
     missing
    0.23
     testim
    0.23
    Activations Density 1.298%

    No Known Activations