© 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. 41218
    Prev
    Next
    INDEX
    Explanations

    change

    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
     rid
    -0.30
    æł·
    -0.28
     observing
    -0.27
    éĩįçĤ¹
    -0.26
     present
    -0.26
    åĮºåŁŁåĨħ
    -0.25
     observation
    -0.25
    æķ²
    -0.25
    åIJ¹
    -0.25
     reversed
    -0.24
    POSITIVE LOGITS
    _CBC
    0.26
    èŁĢ
    0.26
     weren
    0.26
     Sandbox
    0.25
    ä¸Ģ家人
    0.25
     polish
    0.24
    bucks
    0.24
    iblings
    0.23
    amac
    0.23
    peria
    0.23
    Activations Density 0.457%

    No Known Activations