© 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. 40054
    Prev
    Next
    INDEX
    Explanations

    ap

    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
    ordes
    -0.27
    incare
    -0.26
     campaigners
    -0.25
    ÑĢог
    -0.25
     Enable
    -0.25
     onward
    -0.25
    ao
    -0.25
    ÑĢиÑģÑĤ
    -0.24
    perial
    -0.24
    ECH
    -0.24
    POSITIVE LOGITS
     Cyrus
    0.27
    笼
    0.26
    å¾®åįļ
    0.25
    å°¤
    0.25
    åįļ客
    0.25
     haze
    0.24
    亦
    0.24
    åıijæĺİ
    0.24
    çŃīçŃī
    0.24
    (thing
    0.24
    Activations Density 0.674%

    No Known Activations