© 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. 23737
    Prev
    Next
    INDEX
    Explanations

    are

    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
    èĢĥå¯Ł
    -0.28
    åľ¨æĪijçļĦ
    -0.27
    NESS
    -0.26
    éĻĽä¸ĭ
    -0.26
    –
    -0.26
    åĪĽæĸ°
    -0.26
    ä¼łè¯´
    -0.25
    woke
    -0.25
    ograph
    -0.25
    æīįä¼ļ
    -0.24
    POSITIVE LOGITS
    .shtml
    0.30
    çIJĨçĶ±
    0.29
     uncomfortable
    0.29
     uncomfort
    0.28
    æĬ½åıĸ
    0.28
    .Transfer
    0.27
    çĸ
    0.27
    agrams
    0.27
    vince
    0.26
    çĥ¦èºģ
    0.26
    Activations Density 0.001%

    No Known Activations