© 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. 219
    Prev
    Next
    INDEX
    Explanations

    surround

    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
    position
    -0.28
    æĬµ
    -0.26
    æĬ¢åħĪ
    -0.26
     Slo
    -0.25
    à¸łà¸²à¸ŀ
    -0.25
     china
    -0.24
    好åIJĥ
    -0.24
     execution
    -0.24
    POSITION
    -0.24
    éĹ´éļĶ
    -0.24
    POSITIVE LOGITS
     INCIDENT
    0.33
     Incident
    0.27
     explo
    0.26
    olla
    0.26
     surrounding
    0.26
     ranger
    0.25
    iscard
    0.25
    .Ent
    0.25
     adulti
    0.24
    oe
    0.24
    Activations Density 0.016%

    No Known Activations