© 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. 129574
    Prev
    Next
    INDEX
    Explanations

    cases

    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
    ikon
    -0.28
    .gb
    -0.27
    vier
    -0.27
     camb
    -0.27
    CustomAttributes
    -0.25
    vw
    -0.25
    ç°§
    -0.24
     kb
    -0.24
    ocard
    -0.24
    è§Ĥ
    -0.24
    POSITIVE LOGITS
    ÅŁt
    0.27
    erd
    0.27
    å°ıåѦ
    0.26
     flotation
    0.25
    åĪĨ娩
    0.24
    rowCount
    0.24
    éĤ®
    0.24
    nts
    0.23
    æºIJ
    0.23
    erp
    0.23
    Activations Density 0.032%

    No Known Activations