© 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. 161873
    Prev
    Next
    INDEX
    Explanations

    be

    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
    иÑĤелÑĮ
    -0.32
     ul
    -0.28
     buckets
    -0.28
     New
    -0.26
    åºŃ
    -0.26
    kB
    -0.25
     rub
    -0.25
     que
    -0.25
    PTY
    -0.25
     ÑĢÑĥб
    -0.24
    POSITIVE LOGITS
    cesso
    0.27
    alars
    0.26
    ityEngine
    0.26
     compañero
    0.26
    spring
    0.25
    æĺ¯æ²¡æľī
    0.25
    Clickable
    0.25
    æ¤Ĵ
    0.25
    oks
    0.25
    npos
    0.24
    Activations Density 0.047%

    No Known Activations