© 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. 96633
    Prev
    Next
    INDEX
    Explanations

    BER

    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
    among
    -0.30
    mans
    -0.29
     shadow
    -0.29
    åıªä¼ļ
    -0.28
     among
    -0.26
    hardt
    -0.26
    backs
    -0.25
    hom
    -0.25
     cass
    -0.25
     Shack
    -0.25
    POSITIVE LOGITS
     antic
    0.25
    /fs
    0.25
    idf
    0.24
    èī®
    0.24
    .pan
    0.24
    å¼¥
    0.24
     bât
    0.24
    ä¾µåįł
    0.23
    fs
    0.23
    æ¶ĪèĢĹ
    0.23
    Activations Density 0.883%

    No Known Activations