© 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. 162921
    Prev
    Next
    INDEX
    Explanations

    based

    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
    ling
    -0.29
    uhl
    -0.27
    Verse
    -0.26
     spoiled
    -0.26
    plant
    -0.25
    visual
    -0.25
    家çĶµ
    -0.24
    identally
    -0.24
    .hardware
    -0.24
    :start
    -0.24
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡Į
    0.27
    åĨµ
    0.27
    ients
    0.26
    å´Ń
    0.26
    çģµæķı
    0.25
    åħ·ä½ĵæĥħåĨµ
    0.25
    zion
    0.25
    zos
    0.24
    çļĦæĥħåĨµ
    0.24
    ám
    0.24
    Activations Density 0.026%

    No Known Activations