© 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. 19492
    Prev
    Next
    INDEX
    Explanations

    first-person perspective

    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
    ä¸įèĪį
    -0.27
    ehler
    -0.27
    ä»ĩ
    -0.27
    ä»ķ
    -0.27
    ä¸įçĪ±
    -0.26
    ä¸įçĦ¶
    -0.26
    çĭ¼
    -0.26
    大æĸ¹
    -0.26
    fil
    -0.25
    emark
    -0.25
    POSITIVE LOGITS
     acting
    0.32
     acted
    0.32
     acts
    0.31
    act
    0.30
    严éĩį
    0.30
     act
    0.27
     got
    0.27
    acting
    0.27
     Acts
    0.27
    离
    0.26
    Activations Density 0.500%

    No Known Activations