© 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. 95959
    Prev
    Next
    INDEX
    Explanations

    contains the letter i

    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
    åĵī
    -0.27
    ideo
    -0.27
    missive
    -0.25
    éħŀ
    -0.25
     cous
    -0.25
    æĸĹ
    -0.24
    oulos
    -0.24
    affen
    -0.23
    brero
    -0.23
    ä¾£
    -0.23
    POSITIVE LOGITS
     i
    1.63
    	i
    1.24
    _i
    1.24
    (i
    1.18
    -i
    1.17
    {i
    1.16
    =i
    1.16
    i
    1.14
    ,i
    1.14
    *i
    1.13
    Activations Density 0.979%

    No Known Activations