© 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. 24604
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åºŀ
    -0.26
    èĮ
    -0.25
    å¥Ħ
    -0.25
    åıij声
    -0.25
    æķ£åıij
    -0.24
    zens
    -0.24
    verb
    -0.24
    缴åĪ°
    -0.24
    z
    -0.24
    奥
    -0.24
    POSITIVE LOGITS
     suce
    0.25
     laten
    0.24
    mph
    0.24
    -mount
    0.24
     mounts
    0.24
    stadt
    0.24
     mpg
    0.24
     mount
    0.23
    cff
    0.23
     advise
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.