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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163443
    Prev
    Next
    INDEX
    Explanations

    2

    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
     entr
    -0.31
     Sponsor
    -0.27
    trag
    -0.27
    .Entry
    -0.26
    è¶Ł
    -0.26
    etsy
    -0.26
    æĩ·
    -0.26
     pó
    -0.25
     Reyn
    -0.25
    gni
    -0.24
    POSITIVE LOGITS
     pres
    0.28
    cene
    0.28
    érica
    0.26
    thon
    0.26
    omet
    0.26
    oner
    0.26
    sil
    0.26
    pres
    0.25
    Sil
    0.25
    IMA
    0.24
    Activations Density 0.054%

    No Known Activations