© 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. 39631
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    iates
    -0.30
    itch
    -0.27
     Pact
    -0.26
    ality
    -0.26
     Clause
    -0.25
     appropriately
    -0.25
    act
    -0.24
    adium
    -0.24
    akt
    -0.24
    emic
    -0.24
    POSITIVE LOGITS
    æĸ°æĺ¥
    0.27
    rô
    0.25
    rina
    0.24
    è¿Ļ对
    0.24
    ä¸ĢéĹª
    0.24
    rá
    0.24
    .Transactional
    0.23
    çŃīäºİ
    0.23
    ç³»
    0.23
    ç¥ĸçĪ¶
    0.23
    Activations Density 1.596%

    No Known Activations