© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 346
    Prev
    Next
    INDEX
    Explanations

    roc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩłå¼ł
    -0.29
    modifiable
    -0.28
    CED
    -0.27
    ableObject
    -0.27
    oxy
    -0.27
    iode
    -0.27
    erin
    -0.26
    enden
    -0.26
    han
    -0.26
    robat
    -0.26
    POSITIVE LOGITS
     masses
    0.29
    EM
    0.26
     em
    0.26
    äºĴ
    0.25
    æĩĭ
    0.25
    çĮ«
    0.24
    éĢļ
    0.23
     <=>
    0.23
    RefPtr
    0.23
    é¢Ĩ导人
    0.23
    Activations Density 0.010%

    No Known Activations