© 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. 19-TRANSCODER-HP
    7. 6130
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįĥåı¤
    -0.27
    诣
    -0.26
     '\'
    -0.25
     íļĮ
    -0.24
    oman
    -0.24
    ryn
    -0.23
    essler
    -0.23
    McC
    -0.23
     legion
    -0.23
    SHARE
    -0.23
    POSITIVE LOGITS
    iffany
    0.27
    临
    0.26
    raits
    0.25
    uffy
    0.25
    ifa
    0.24
    iefs
    0.24
    Rnd
    0.24
    çĭ¸
    0.24
    æ´Ĺè¡£
    0.24
    迤
    0.24
    Activations Density 0.016%

    No Known Activations