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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130140
    Prev
    Next
    INDEX
    Explanations

    Short sounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįļ主
    -0.27
    oon
    -0.27
    agos
    -0.26
    ees
    -0.25
    izedName
    -0.25
     privile
    -0.24
    getic
    -0.23
    ÑĪек
    -0.23
    licit
    -0.23
    äºĨåįĬ天
    -0.23
    POSITIVE LOGITS
    å°ıé¾Ļ
    0.25
    acer
    0.25
     cab
    0.25
    æĥ³è¦ģ
    0.25
     jan
    0.25
    èľ¡
    0.24
    çĿĢ
    0.24
    oce
    0.24
    çİ°åľ¨
    0.23
    ãĥ§ãĥ³
    0.23
    Activations Density 0.060%

    No Known Activations