© 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. 14-TRANSCODER-HP
    7. 39973
    Prev
    Next
    INDEX
    Explanations

    astronomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ire
    -0.27
    read
    -0.27
     unique
    -0.25
    ister
    -0.24
    ost
    -0.24
    -read
    -0.24
     sc
    -0.24
    强迫
    -0.24
    使èĢħ
    -0.24
    ç»ıè¿ĩå¤ļå¹´
    -0.23
    POSITIVE LOGITS
    è¦ģåĬłå¼º
    0.30
    ni
    0.28
     BASIS
    0.26
     strictly
    0.25
    DAQ
    0.25
     tweaking
    0.25
     ni
    0.25
    ä¸įå¼Ģ
    0.25
     consolidate
    0.25
     practise
    0.24
    Activations Density 0.023%

    No Known Activations