© 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. 150995
    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
    åıij
    -0.30
    å±ħ
    -0.28
    DBG
    -0.26
    &utm
    -0.26
    çĪ·çĪ·
    -0.26
    å°Ħ
    -0.26
    æĶ¯ä»ĺ
    -0.25
     mainAxisAlignment
    -0.25
    imming
    -0.25
    纪念ç¢ij
    -0.25
    POSITIVE LOGITS
    MX
    0.24
    çĶŁåij½
    0.24
     fuzz
    0.24
    icted
    0.24
     execution
    0.24
     budd
    0.23
     Artifact
    0.23
     MSR
    0.23
     grouped
    0.23
     Tá»Ń
    0.23
    Activations Density 0.270%

    No Known Activations

    This feature has no known activations.