© 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. 27-TRANSCODER-HP
    7. 58288
    Prev
    Next
    INDEX
    Explanations

    dataset text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľåĩºäºĨ
    -0.32
    çķĻä¸ĭæĿ¥
    -0.29
    æĭ¿åĩºæĿ¥
    -0.27
    æĥ³èµ·äºĨ
    -0.26
    Else
    -0.26
    è¿ĩäºĨ
    -0.26
    stime
    -0.26
    åģļåĩºäºĨ
    -0.26
    wer
    -0.25
    çľĭäºĨ
    -0.25
    POSITIVE LOGITS
     first
    0.31
    ¬ģ
    0.30
     pencil
    0.27
    [first
    0.27
     permanently
    0.26
    quin
    0.26
     susp
    0.25
    ches
    0.24
     FIRST
    0.24
     arms
    0.24
    Activations Density 0.001%

    No Known Activations