© 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. 130540
    Prev
    Next
    INDEX
    Explanations

    formal text

    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
     honor
    -0.28
    æ´ĹåĩĢ
    -0.27
    ksam
    -0.27
     getS
    -0.26
     Kb
    -0.26
    æĪIJéķ¿
    -0.26
    bic
    -0.25
    æĬĵç´§
    -0.25
    æī°ä¹±
    -0.25
    qb
    -0.24
    POSITIVE LOGITS
    ISS
    0.32
    å®ŀè´¨
    0.31
    ipsoid
    0.28
    çµIJ
    0.26
    zos
    0.26
    ophysical
    0.26
     prim
    0.26
    ç»ĵ
    0.26
     mac
    0.25
    MAC
    0.25
    Activations Density 0.004%

    No Known Activations