© 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. 361
    Prev
    Next
    INDEX
    Explanations

    Lawrence

    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
    compat
    -0.28
    æľº
    -0.26
    ifications
    -0.26
    æ¡Ĩæŀ¶
    -0.26
    ward
    -0.26
    å½±
    -0.25
    aware
    -0.25
    iators
    -0.25
    并ä¸İ
    -0.25
    frame
    -0.24
    POSITIVE LOGITS
    anela
    0.26
    çĤĶ
    0.26
    évolution
    0.25
    ben
    0.24
     ка
    0.24
    xffffffff
    0.24
    assage
    0.24
     lẽ
    0.23
    Dod
    0.23
    æĶĢçĻ»
    0.23
    Activations Density 0.014%

    No Known Activations