© 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. 22-TRANSCODER-HP
    7. 129195
    Prev
    Next
    INDEX
    Explanations

    approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thus
    -0.28
     hence
    -0.27
    pers
    -0.25
     donc
    -0.25
     therefore
    -0.24
     thereby
    -0.24
    ä¸įæĢķ
    -0.24
    æłħ
    -0.24
    /change
    -0.24
    OMET
    -0.23
    POSITIVE LOGITS
    kit
    0.25
    çļĦæĥħå½¢
    0.25
    {{{
    0.25
    adol
    0.25
     unheard
    0.25
     spots
    0.25
    ðŁı»
    0.25
    æĹıèĩªæ²»åİ¿
    0.24
    -directed
    0.24
    èĹĵ
    0.24
    Activations Density 0.009%

    No Known Activations