© 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. 95583
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
    unate
    -0.26
    ableObject
    -0.26
    indre
    -0.26
     ngoại
    -0.26
     mild
    -0.26
     minority
    -0.25
    æģķ
    -0.25
     particular
    -0.25
    ivy
    -0.24
    ierge
    -0.24
    POSITIVE LOGITS
     by
    0.50
    çĶ±
    0.42
     oleh
    0.34
    by
    0.33
     through
    0.33
    _by
    0.32
     at
    0.32
     in
    0.31
     bợi
    0.31
    çĶ±ä¸ŃåĽ½
    0.30
    Activations Density 0.027%

    No Known Activations