© 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. 18-TRANSCODER-HP
    7. 89452
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cit
    -0.26
     institutes
    -0.26
    室åĨħ
    -0.25
    Ja
    -0.25
     camps
    -0.25
    camp
    -0.25
     OnInit
    -0.24
    çľ¼åīį
    -0.24
    iets
    -0.24
    ÑĮ
    -0.24
    POSITIVE LOGITS
    cher
    0.28
    çīĮ
    0.26
     choke
    0.25
    éĢįéģ¥
    0.25
    èĩªçĶ±è´¸æĺĵ
    0.25
    ocio
    0.24
    ndl
    0.24
     Freem
    0.24
     Extras
    0.24
    çķĻè¨ĢæĿ¿
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.