© 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. 40739
    Prev
    Next
    INDEX
    Explanations

    h

    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
    缸
    -0.26
    ä¸Ī夫
    -0.26
    hart
    -0.26
     phase
    -0.26
    {l
    -0.24
     Rif
    -0.24
     displacement
    -0.23
    roz
    -0.23
     deadliest
    -0.23
     stranger
    -0.23
    POSITIVE LOGITS
     AQ
    0.32
    ãĤģãĤĭ
    0.28
    owler
    0.28
     Ven
    0.28
    ç¿ĺ
    0.27
    ãĤģãģŁ
    0.26
    aqu
    0.25
    èĢĥãģĪãĤĭ
    0.25
     undert
    0.25
    ioc
    0.25
    Activations Density 0.461%

    No Known Activations