© 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. 9-TRANSCODER-HP
    7. 30085
    Prev
    Next
    INDEX
    Explanations

    rain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.31
    tons
    -0.28
    ç²ī
    -0.28
    cepts
    -0.27
    èµ
    -0.27
    ами
    -0.26
     tantr
    -0.26
     succeed
    -0.26
    è¶ĬæĿ¥
    -0.26
     SUCCESS
    -0.25
    POSITIVE LOGITS
    roll
    0.27
    emb
    0.26
     Zodiac
    0.25
    _Record
    0.25
     roll
    0.24
    å¹´ä¹ĭ
    0.24
    encer
    0.24
    ä¸ĢæĿ¡é¾Ļ
    0.23
    ç®±åŃIJ
    0.23
    acio
    0.23
    Activations Density 0.279%

    No Known Activations