© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96328
    Prev
    Next
    INDEX
    Explanations

    stat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Plane
    -0.31
    plane
    -0.31
     Plane
    -0.31
     plane
    -0.30
    å®ļä¹ī
    -0.28
    åŀĤ
    -0.27
     drama
    -0.26
     vertical
    -0.26
    loor
    -0.26
    PL
    -0.26
    POSITIVE LOGITS
    Sac
    0.31
     sac
    0.28
     Sac
    0.27
    orative
    0.27
    å½ķ
    0.26
    æĸĩçĮ®
    0.25
    çļĦæ¯Ķä¾ĭ
    0.25
    ersh
    0.25
    meld
    0.25
    endum
    0.24
    Activations Density 0.002%

    No Known Activations