© 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. 162046
    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_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
    iente
    -0.27
    顺
    -0.26
     itself
    -0.26
    nearest
    -0.25
    .Ignore
    -0.25
     oneself
    -0.25
    éĻŁ
    -0.25
    è°Ī
    -0.25
     yourself
    -0.24
    itr
    -0.24
    POSITIVE LOGITS
    warts
    0.28
    emer
    0.26
    ()._
    0.25
    Constructed
    0.24
    esium
    0.23
    _STARTED
    0.23
    serter
    0.23
    BUM
    0.23
    olas
    0.23
    è¢Ħ
    0.23
    Activations Density 0.009%

    No Known Activations