© 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. 22-TRANSCODER-HP
    7. 111569
    Prev
    Next
    INDEX
    Explanations

    money and prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elihood
    -0.27
     INCLUDED
    -0.26
    ctal
    -0.26
    å±Ģå±Ģéķ¿
    -0.25
    adden
    -0.24
     drowned
    -0.24
    _BLEND
    -0.23
    arrival
    -0.23
     accent
    -0.23
    anine
    -0.22
    POSITIVE LOGITS
    ex
    0.29
    äºīåıĸ
    0.27
    obil
    0.27
    otify
    0.27
    oss
    0.27
    yx
    0.27
    :
    0.26
    è¿Ļæīį
    0.26
    _SY
    0.26
    yro
    0.25
    Activations Density 0.049%

    No Known Activations