© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23694
    Prev
    Next
    INDEX
    Explanations

    grammatically correct English text

    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
    以人æ°ij
    -0.26
     stoi
    -0.25
    壬
    -0.25
    ãģ«ãģªãĤĬãģ¾ãģĹãģŁ
    -0.25
    æ¸ħåĩī
    -0.24
     MPS
    -0.24
    ãĥIJãĥ©ãĥ³ãĤ¹
    -0.24
    овал
    -0.24
    没äºĨ
    -0.24
    æ°´ä¸Ĭ
    -0.23
    POSITIVE LOGITS
     studies
    0.30
     caution
    0.29
    ich
    0.28
     someone
    0.28
     stars
    0.28
     ones
    0.28
    someone
    0.28
    immer
    0.27
     Someone
    0.27
     something
    0.25
    Activations Density 0.004%

    No Known Activations