© 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. 87400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åīª
    -0.27
    <Field
    -0.27
    çģ«çĥ§
    -0.26
     specialized
    -0.25
    /spec
    -0.24
    追
    -0.24
    esthesia
    -0.23
    ä¸ĵéŨ
    -0.23
    款
    -0.23
     Cycling
    -0.23
    POSITIVE LOGITS
    éħ¿éĢł
    0.30
    æİĸ
    0.25
    -org
    0.25
    =root
    0.25
    ä¸Ģ侧
    0.24
    -alert
    0.24
    elper
    0.23
    -git
    0.23
    çķĻåŃĺ
    0.23
     rounded
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.