© 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. 18905
    Prev
    Next
    INDEX
    Explanations

    article "the" or "a"

    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
    侧
    -0.31
    base
    -0.27
    /Area
    -0.26
    æŁ±
    -0.26
     base
    -0.26
    ory
    -0.26
    bane
    -0.26
    ateral
    -0.26
    zte
    -0.26
    day
    -0.25
    POSITIVE LOGITS
     joints
    0.28
    Pid
    0.28
    åģľäº§
    0.27
     mus
    0.26
    ters
    0.25
     Flo
    0.25
     scre
    0.25
    ç¼ĩ
    0.25
    çŃĽ
    0.25
    mus
    0.25
    Activations Density 0.472%

    No Known Activations