© 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. 23-TRANSCODER-HP
    7. 162004
    Prev
    Next
    INDEX
    Explanations

    course

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aval
    -0.30
    ény
    -0.28
    çĥĤ
    -0.27
    gap
    -0.27
    olar
    -0.25
    olla
    -0.25
    éħį
    -0.25
    RequestId
    -0.25
     waive
    -0.25
    ension
    -0.25
    POSITIVE LOGITS
    缮
    0.32
     Viktor
    0.28
    åĨħ容
    0.27
    çĶ±ä¸ŃåĽ½
    0.27
    scribers
    0.26
    åIJ¸å¼ķäºĨ
    0.25
    -ce
    0.24
    çļĦåĨħ容
    0.23
     Vij
    0.23
    缮ãģ«
    0.23
    Activations Density 0.006%

    No Known Activations