© 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. 31-TRANSCODER-HP
    7. 18577
    Prev
    Next
    INDEX
    Explanations

    cumulative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Complex
    -0.28
    çIJĨ论ä¸Ĭ
    -0.26
    :`~
    -0.26
    çIJĨ论
    -0.26
    tn
    -0.25
    åıį
    -0.25
    ä¸į容
    -0.25
    æ¥ŀ
    -0.25
    complex
    -0.25
     Theory
    -0.25
    POSITIVE LOGITS
    apus
    0.30
    çĮĸ
    0.30
     innings
    0.29
    cks
    0.28
     stocking
    0.26
    æ±ĩ
    0.26
    amel
    0.26
    mai
    0.25
    åħħå®ŀ
    0.25
    ilate
    0.25
    Activations Density 0.008%

    No Known Activations