© 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. 18744
    Prev
    Next
    INDEX
    Explanations

    question/answer context

    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
     acting
    -0.52
    ä½ľçĶ¨
    -0.46
     acts
    -0.46
     acted
    -0.45
    acting
    -0.45
     Acts
    -0.42
    acts
    -0.42
     Act
    -0.41
     Acting
    -0.40
     act
    -0.38
    POSITIVE LOGITS
     achieve
    0.35
    allow
    0.33
     Give
    0.31
    Give
    0.31
    Allow
    0.31
    åģļåĪ°
    0.30
    icom
    0.30
     stand
    0.29
    Achie
    0.29
     Allow
    0.28
    Activations Density 0.131%

    No Known Activations