© 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. 14-TRANSCODER-HP
    7. 40429
    Prev
    Next
    INDEX
    Explanations

    Demonstrative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leen
    -0.27
    IVO
    -0.26
    ivo
    -0.25
     sts
    -0.25
    ber
    -0.25
    çĥŃ带
    -0.24
     Farmer
    -0.24
     nonetheless
    -0.24
     chats
    -0.23
    :http
    -0.23
    POSITIVE LOGITS
    éĴ
    0.26
    andon
    0.25
    人äºĭ
    0.25
    ukkan
    0.25
    â¼Ŀ
    0.25
     Gul
    0.24
    é¢Ĩ
    0.24
    etsk
    0.24
    é«ĺçŃī
    0.24
     Saud
    0.24
    Activations Density 0.073%

    No Known Activations