© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7132
    Prev
    Next
    INDEX
    Explanations

    few

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħĭæĸ¯
    -0.25
     Bonds
    -0.25
    mia
    -0.25
    ulant
    -0.25
    ulk
    -0.24
    ät
    -0.24
    ivant
    -0.24
    íķĺ
    -0.24
    æѦåĬŁ
    -0.24
    ivities
    -0.24
    POSITIVE LOGITS
    ndata
    0.28
    zzle
    0.27
    AUSE
    0.26
    pus
    0.25
    æķĻçłĶ
    0.25
    Tam
    0.25
    æĿ¥çļĦ
    0.24
    èĥ½åģļåĪ°
    0.24
     refute
    0.24
     HARD
    0.23
    Activations Density 0.970%

    No Known Activations