© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    long, technical texts

    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
    åĽĽæĸ¹
    -0.26
     genetically
    -0.26
    bih
    -0.26
    pawn
    -0.25
    LAG
    -0.24
    gmt
    -0.24
    icopt
    -0.24
     borough
    -0.24
    Networking
    -0.24
    åİŁä»¶
    -0.24
    POSITIVE LOGITS
     someone
    0.31
     alguém
    0.28
    èµ·
    0.27
     Someone
    0.26
     trial
    0.26
    ä¸Ģ个人
    0.26
     somebody
    0.26
    ).\
    0.26
    olut
    0.25
     persona
    0.25
    Activations Density 25.151%

    No Known Activations