© 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. 129814
    Prev
    Next
    INDEX
    Explanations

    accented characters

    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
    ity
    -0.40
    i
    -0.31
    ator
    -0.31
    át
    -0.29
    ere
    -0.29
    ery
    -0.28
    ient
    -0.28
    n
    -0.28
     sup
    -0.28
    a
    -0.28
    POSITIVE LOGITS
    驼
    0.26
    ndata
    0.25
    verty
    0.25
    éĻ·éĺ±
    0.25
    eff
    0.24
    峪
    0.23
    ece
    0.23
    HEME
    0.23
    scheme
    0.22
    FOUNDATION
    0.22
    Activations Density 0.026%

    No Known Activations