© 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. 29722
    Prev
    Next
    INDEX
    Explanations

    instruct

    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
     earning
    -0.27
    icut
    -0.26
     earnings
    -0.26
    .axes
    -0.25
    éĤĢ
    -0.25
     earned
    -0.25
    åĬ«
    -0.25
    anded
    -0.25
     busted
    -0.25
    vvm
    -0.25
    POSITIVE LOGITS
     Bark
    0.30
    èĥĮçĿĢ
    0.26
    íķĢ
    0.26
    çļĤ
    0.25
    swith
    0.25
    åIJ»
    0.25
    reader
    0.24
    ritel
    0.24
    ingly
    0.24
    teness
    0.24
    Activations Density 0.911%

    No Known Activations