© 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. 19-TRANSCODER-HP
    7. 9162
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Pivot
    -0.27
     discharged
    -0.26
    ToOne
    -0.25
    责任å¿ĥ
    -0.25
    ANCES
    -0.24
    usive
    -0.24
    _Options
    -0.24
    uled
    -0.24
     Carroll
    -0.24
    apps
    -0.24
    POSITIVE LOGITS
    ãģķãģ¾
    0.30
    va
    0.25
    çIJĨ
    0.25
     anda
    0.25
    unda
    0.25
    ãģ¾ãģŁ
    0.24
    0.24
     |↵↵
    0.24
    iam
    0.24
    *
    0.24
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.