© 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. 95301
    Prev
    Next
    INDEX
    Explanations

    About installation or mounting

    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
    kid
    -0.28
    CodeGen
    -0.27
    æ¶ķ
    -0.27
    é¦ĸåıij
    -0.27
    æĸ°è¥¿
    -0.26
    å¥Ĺè·¯
    -0.25
    inality
    -0.25
     Elite
    -0.24
    æĮ¡
    -0.24
    PUTE
    -0.24
    POSITIVE LOGITS
     mounts
    0.42
     mounting
    0.40
     mounted
    0.39
    å®īè£ħ
    0.38
     installed
    0.38
     installation
    0.36
    -mounted
    0.35
    installed
    0.35
     mount
    0.35
    mounted
    0.34
    Activations Density 1.031%

    No Known Activations