© 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. 22724
    Prev
    Next
    INDEX
    Explanations

    Earth

    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
    emen
    -0.26
    èħĭ
    -0.26
    gree
    -0.25
    kı
    -0.25
    alker
    -0.25
    淹没
    -0.25
    æĵIJ
    -0.25
    Boost
    -0.24
    个å¤ļ
    -0.24
    èĦļ
    -0.24
    POSITIVE LOGITS
    reason
    0.26
    Away
    0.25
    ÑģÑĤи
    0.25
     пÑĢоб
    0.25
    minute
    0.25
    åĢŁåı£
    0.24
    frared
    0.24
    Direct
    0.24
    çĤ¬
    0.24
    .RegisterType
    0.24
    Activations Density 0.001%

    No Known Activations