© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6053
    Prev
    Next
    INDEX
    Explanations

    "5", "Fifth" or "IR"

    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
    ables
    -0.27
    Pts
    -0.26
    tribute
    -0.25
     Trey
    -0.25
    lish
    -0.24
     atrib
    -0.24
    inium
    -0.24
    ierz
    -0.24
    iers
    -0.23
    iene
    -0.23
    POSITIVE LOGITS
    OrNull
    0.27
    ä¼ĬåĪ©
    0.25
    staff
    0.25
     staff
    0.24
    èĢ³
    0.24
    à¹ģà¸Ĺ
    0.24
    unlikely
    0.24
    ilo
    0.23
    igure
    0.23
    ago
    0.23
    Activations Density 0.010%

    No Known Activations