© 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. 35-TRANSCODER-HP
    7. 40042
    Prev
    Next
    INDEX
    Explanations

    Scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     severed
    -0.27
     suffice
    -0.26
    æĹłçŁ¥
    -0.25
    ãģ¾ãģ¾
    -0.24
     paralyzed
    -0.24
    ä¸Ģå®ļç¨ĭ度
    -0.23
     collide
    -0.23
    ä¸Ģ带
    -0.23
    æĢ¥äºİ
    -0.23
     cling
    -0.22
    POSITIVE LOGITS
    nin
    0.47
    n
    0.45
    ci
    0.44
    gan
    0.41
    don
    0.41
    dan
    0.40
    ite
    0.40
    iti
    0.40
    ders
    0.40
    st
    0.40
    Activations Density 42.519%

    No Known Activations