© 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. 130014
    Prev
    Next
    INDEX
    Explanations

    v

    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
    åĸ·
    -0.26
    iali
    -0.23
    gv
    -0.23
     FAILURE
    -0.23
    çĮ¿
    -0.23
    Äĥr
    -0.23
    åĻ´
    -0.23
     discouraged
    -0.22
    roid
    -0.22
     mor
    -0.22
    POSITIVE LOGITS
    临æŶ
    0.31
    åĩŃ
    0.27
     slow
    0.27
    çİ°å®ŀ
    0.27
    slow
    0.26
    idar
    0.26
    .mods
    0.25
    antine
    0.25
    Slow
    0.24
    éļıæŶ
    0.24
    Activations Density 0.006%

    No Known Activations