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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 73
    Prev
    Next
    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFY
    -0.28
    pora
    -0.26
    ify
    -0.26
    olum
    -0.26
    äch
    -0.25
    reau
    -0.25
    олов
    -0.25
    iale
    -0.25
    acci
    -0.25
    (strict
    -0.25
    POSITIVE LOGITS
    å§ĭç»ĪåĿļæĮģ
    0.28
     bald
    0.24
    speaker
    0.23
    ç¾İ好
    0.23
    .createComponent
    0.23
    multip
    0.23
    AdapterManager
    0.22
     Speaker
    0.22
     Adjustable
    0.22
    _wheel
    0.22
    Activations Density 0.015%

    No Known Activations