© 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. 24-TRANSCODER-HP
    7. 150016
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tall
    -0.28
    å°±è¶Ĭ
    -0.27
    anta
    -0.27
    ä¸įå¦Ĥ
    -0.27
    ical
    -0.26
    -forward
    -0.25
    ensitive
    -0.25
     cert
    -0.25
    adle
    -0.25
    èĩªä¿¡
    -0.25
    POSITIVE LOGITS
     humid
    0.29
    eken
    0.26
     genie
    0.25
    czy
    0.25
     molec
    0.25
     formation
    0.24
     acess
    0.24
     concession
    0.24
    oley
    0.24
     insertion
    0.23
    Activations Density 0.500%

    No Known Activations

    This feature has no known activations.