© 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. 96697
    Prev
    Next
    INDEX
    Explanations

    He/She

    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
    Had
    -0.29
    æīĢ
    -0.29
    æīĢèĥ½
    -0.28
    éĵº
    -0.28
    åĪĽéĢłäºĨ
    -0.27
    éĢīæĭ©äºĨ
    -0.26
     ecl
    -0.26
    æŁ¥çľĭæĽ´å¤ļ
    -0.26
     Had
    -0.25
    æİ¥åıĹäºĨ
    -0.25
    POSITIVE LOGITS
     even
    0.55
    even
    0.52
     Even
    0.43
    Even
    0.41
     даже
    0.38
    çĶļèĩ³
    0.37
    åį³ä½¿
    0.35
     consider
    0.34
     incluso
    0.33
     nawet
    0.33
    Activations Density 0.912%

    No Known Activations