© 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. 18851
    Prev
    Next
    INDEX
    Explanations

    emphasize

    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
     Complete
    -0.27
    åĮĹè·¯
    -0.26
    ataka
    -0.26
    ager
    -0.26
     rise
    -0.26
    ników
    -0.26
    chter
    -0.26
    opal
    -0.25
     complete
    -0.24
    .SerializeObject
    -0.24
    POSITIVE LOGITS
    Above
    0.38
    ä¸ĬéĿ¢
    0.36
    above
    0.36
     repetition
    0.35
    bove
    0.34
     above
    0.33
     repeated
    0.31
    åıįå¤į
    0.31
    éĩįå¤į
    0.30
    _above
    0.30
    Activations Density 0.995%

    No Known Activations