© 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. 23174
    Prev
    Next
    INDEX
    Explanations

    ian

    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
     Alone
    -0.29
    æīįçŁ¥éģĵ
    -0.27
    .del
    -0.26
    çĮĽçĦ¶
    -0.25
    æĮ¯å¥ĭ
    -0.25
    outers
    -0.25
    HostName
    -0.25
    çĶ³æĬ¥
    -0.24
    final
    -0.24
    udos
    -0.24
    POSITIVE LOGITS
     rollout
    0.27
    enet
    0.26
    Ñĩки
    0.26
    )p
    0.25
     Ev
    0.24
    Sequential
    0.24
    cá
    0.24
    cq
    0.23
    OLL
    0.23
    -w
    0.23
    Activations Density 0.040%

    No Known Activations