© 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. 96168
    Prev
    Next
    INDEX
    Explanations

    maid/maiden

    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
    Uses
    -0.27
    æĺ¼
    -0.26
     TL
    -0.25
    æĵį
    -0.25
    .hu
    -0.25
    iforn
    -0.25
    å°ĸ
    -0.25
    çł´
    -0.25
     brief
    -0.24
     Uses
    -0.24
    POSITIVE LOGITS
    oid
    0.30
    ä¸įä¸ĭ
    0.28
    åı¯æĢľ
    0.28
    loo
    0.26
    lick
    0.25
    è´ŀ
    0.25
    ingly
    0.25
    OfSize
    0.25
    容
    0.24
    elf
    0.24
    Activations Density 0.002%

    No Known Activations