© 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. 161744
    Prev
    Next
    INDEX
    Explanations

    Licenses and legal text

    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
     Ble
    -0.30
     sire
    -0.25
     agre
    -0.24
    cka
    -0.24
    ä¸ĭæ²ī
    -0.24
    who
    -0.24
     Dam
    -0.24
    çİ«çij°
    -0.23
     who
    -0.23
    ble
    -0.23
    POSITIVE LOGITS
     scoped
    0.28
    TEL
    0.27
    éļ½
    0.26
    èĭ±
    0.26
    rete
    0.25
    üst
    0.25
    å°ĺ
    0.25
    ByExample
    0.24
    骤
    0.24
    æİĽ
    0.24
    Activations Density 0.126%

    No Known Activations