© 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. 162951
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    èĩªæľī
    -0.28
    åħ¬å¼Ģ课
    -0.27
    å¤ļ个
    -0.27
    大éĩı
    -0.27
    æľī两个
    -0.27
     several
    -0.26
    graded
    -0.26
    ä¸Ģå¥Ĺ
    -0.25
    å¾Īç®Ģåįķ
    -0.25
     very
    -0.25
    POSITIVE LOGITS
    ä¹ĭæĥħ
    0.26
     plane
    0.26
     break
    0.25
     sentimental
    0.25
    roman
    0.25
     "{{
    0.24
     ex
    0.24
     Usa
    0.24
    tle
    0.24
     rom
    0.24
    Activations Density 0.026%

    No Known Activations