© 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. 27-TRANSCODER-HP
    7. 56746
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seiz
    -0.27
    æĺ¯ä»Ģä¹Īåij¢
    -0.27
     charismatic
    -0.27
     jails
    -0.26
    acob
    -0.26
     Hospitals
    -0.26
     hospitals
    -0.25
    ño
    -0.25
     ÑĥвеÑĢен
    -0.25
    ohana
    -0.24
    POSITIVE LOGITS
     thickness
    0.33
     payload
    0.31
    转æĬĺ
    0.30
    è´Łè½½
    0.30
     threshold
    0.29
     total
    0.29
    éĹ¨æ§Ľ
    0.28
     intensity
    0.28
     payloads
    0.28
    uter
    0.27
    Activations Density 0.015%

    No Known Activations