© 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. 163005
    Prev
    Next
    INDEX
    Explanations

    Impulsive/spontaneous actions/decisions

    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
     dop
    -0.26
    使
    -0.26
    马æĭī
    -0.25
    åĩ»
    -0.25
    reveal
    -0.24
    æĭī
    -0.24
    today
    -0.23
    ayout
    -0.23
    ELLOW
    -0.23
     platinum
    -0.23
    POSITIVE LOGITS
    æĢ§çĸ¾çĹħ
    0.28
     improvis
    0.27
    ç¾Į
    0.25
    VRT
    0.25
    èĮ«çĦ¶
    0.25
     textures
    0.24
    ä¸Ģéģį
    0.24
    ÎĨ
    0.24
    Textures
    0.23
    orage
    0.23
    Activations Density 0.005%

    No Known Activations