© 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. 162897
    Prev
    Next
    INDEX
    Explanations

    parents

    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
    .pages
    -0.28
    æıIJçİ°
    -0.26
    erva
    -0.26
    ooke
    -0.26
    esses
    -0.26
    leases
    -0.25
    æīĭä¸ŃçļĦ
    -0.25
    rophe
    -0.25
    esen
    -0.24
    urses
    -0.24
    POSITIVE LOGITS
     alas
    0.28
    -Time
    0.28
    -time
    0.27
    æ¼Ĥ
    0.26
     sourceMappingURL
    0.26
    åºĶåıĬæŶ
    0.26
    Back
    0.25
     jumps
    0.25
    åįģåĩłä¸ª
    0.24
    并å°Ĩ
    0.24
    Activations Density 0.008%

    No Known Activations