© 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. 30-TRANSCODER-HP
    7. 96685
    Prev
    Next
    INDEX
    Explanations

    am or lam

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intervention
    -0.30
     agency
    -0.28
     rev
    -0.28
     reality
    -0.27
     thought
    -0.26
    y
    -0.26
    yen
    -0.26
     usage
    -0.25
     agencies
    -0.25
     challenges
    -0.25
    POSITIVE LOGITS
    /TR
    0.27
    few
    0.26
    .ham
    0.26
    åħ¥
    0.25
    å°Ħ
    0.25
    ect
    0.25
     asm
    0.25
    icine
    0.25
    omi
    0.25
    scriptions
    0.25
    Activations Density 0.003%

    No Known Activations