© 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. 41243
    Prev
    Next
    INDEX
    Explanations

    End of data entries

    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
    è¿Ļç±»
    -0.30
    缮
    -0.28
    _prov
    -0.27
    缮ãģ«
    -0.26
    TTY
    -0.26
    ior
    -0.26
    Found
    -0.26
    线ä¸ĭ
    -0.25
    æŀľ
    -0.25
    DS
    -0.25
    POSITIVE LOGITS
    antas
    0.28
    èį«
    0.26
    progressbar
    0.25
    ä¸Ģå¼Ģå§ĭå°±
    0.25
    ién
    0.25
    ance
    0.25
    èķī
    0.24
    ane
    0.24
    Ñħо
    0.24
     compensated
    0.24
    Activations Density 0.020%

    No Known Activations