© 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. 29625
    Prev
    Next
    INDEX
    Explanations

    education and recent events

    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
    èĹ
    -0.27
    è¤Ĥ
    -0.26
    encies
    -0.26
    èı
    -0.26
     midd
    -0.26
    [assembly
    -0.26
     wxDefault
    -0.25
    outer
    -0.25
    è°±
    -0.25
    cribing
    -0.24
    POSITIVE LOGITS
    çŃĮ
    0.27
    头
    0.27
     Head
    0.27
    ingo
    0.27
    rost
    0.26
    wu
    0.26
    oras
    0.25
    éłŃ
    0.24
     raz
    0.24
    еÑĢÑĤ
    0.24
    Activations Density 0.040%

    No Known Activations