© 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. 95741
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    ITED
    -0.28
    пÑĥÑĤ
    -0.28
    getConnection
    -0.26
    ä¸įåħĭ
    -0.26
    ikon
    -0.24
    _planes
    -0.24
    erals
    -0.24
    aroo
    -0.23
    itti
    -0.23
     Isaiah
    -0.23
    POSITIVE LOGITS
     bé
    0.25
     compt
    0.24
    .rs
    0.24
     demi
    0.24
    åľ°éģĵ
    0.23
     structured
    0.23
    æ·±åħ¥äºĨ解
    0.23
    èĤĵ
    0.23
    bl
    0.23
    éĦļ
    0.23
    Activations Density 0.886%

    No Known Activations