© 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. 12-TRANSCODER-HP
    7. 23449
    Prev
    Next
    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĶ¯ä¸ĢçļĦ
    -0.29
     unique
    -0.27
    çѵ
    -0.27
    pcf
    -0.26
    çĭ¬åħ·
    -0.25
    (int
    -0.25
     hyper
    -0.24
     Tro
    -0.24
     invite
    -0.24
    ration
    -0.24
    POSITIVE LOGITS
    IPP
    0.29
    åį°èĬ±
    0.29
    ông
    0.28
    ä¿Ŀ
    0.26
    transfer
    0.26
     IPs
    0.26
    åįĥ
    0.26
    æĭĶ
    0.26
    ripper
    0.25
     balk
    0.25
    Activations Density 0.002%

    No Known Activations