© 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. 39987
    Prev
    Next
    INDEX
    Explanations

    PBS, URLs, code

    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
     cap
    -0.27
     PURPOSE
    -0.26
     purpose
    -0.26
    ;base
    -0.26
    åİ¥
    -0.26
    OwnerId
    -0.26
     pu
    -0.25
    purpose
    -0.25
    sett
    -0.24
    *pi
    -0.24
    POSITIVE LOGITS
    chw
    0.29
    oire
    0.29
    acker
    0.27
    lb
    0.27
    à¹ī
    0.26
    LB
    0.26
     poids
    0.26
    åħ¬åħ±åį«çĶŁ
    0.26
    æ£ĭ
    0.25
    hiro
    0.25
    Activations Density 0.957%

    No Known Activations