© 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. 162274
    Prev
    Next
    INDEX
    Explanations

    patents and legal documents

    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
    xies
    -0.27
    ulous
    -0.27
    åħ·
    -0.25
    ìŀIJìĿĺ
    -0.25
    ç
    -0.24
    аÑĤÑĥÑĢ
    -0.24
    quoi
    -0.24
    fc
    -0.23
    ìŀIJ
    -0.23
     substitution
    -0.23
    POSITIVE LOGITS
    posting
    0.31
    getPost
    0.28
     feud
    0.28
    publication
    0.28
    à¹īà¸Ńà¸Ļ
    0.27
    compiled
    0.27
    illard
    0.27
    èĮ«èĮ«
    0.25
    -Smith
    0.25
     PSI
    0.24
    Activations Density 0.002%

    No Known Activations