© 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. 23-TRANSCODER-HP
    7. 24844
    Prev
    Next
    INDEX
    Explanations

    travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĪен
    -0.27
    ueur
    -0.26
    HING
    -0.26
    еÑĢÑĮ
    -0.25
    äch
    -0.25
    kel
    -0.25
     setC
    -0.25
    -nil
    -0.24
    éĻĮçĶŁ
    -0.24
    anst
    -0.24
    POSITIVE LOGITS
     and
    0.49
     &
    0.41
     vÃł
    0.40
     ë°ı
    0.35
    åıĬ
    0.34
     и
    0.33
    åıĬãģ³
    0.33
     or
    0.32
    ãģĬãĤĪãģ³
    0.31
     &↵
    0.30
    Activations Density 0.072%

    No Known Activations