© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41481
    Prev
    Next
    INDEX
    Explanations

    Emotions and relationships

    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
    ASSERT
    -0.27
    æ´µ
    -0.27
    utral
    -0.26
    áºĵ
    -0.26
    åĮºæĶ¿åºľ
    -0.26
    iro
    -0.25
    éļį
    -0.25
    (AT
    -0.24
    ucha
    -0.24
    nings
    -0.24
    POSITIVE LOGITS
    aines
    0.30
     precisely
    0.28
    som
    0.27
    aine
    0.26
    çĿ«
    0.24
    æĭĪ
    0.24
     remain
    0.24
    ÑħваÑĤ
    0.24
     Tablets
    0.24
     decis
    0.24
    Activations Density 0.208%

    No Known Activations