© 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. 27-TRANSCODER-HP
    7. 57456
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢĤ
    -0.27
     scale
    -0.27
    relation
    -0.26
    bearing
    -0.25
    pv
    -0.25
    è§Ħ模
    -0.25
    pivot
    -0.25
    aber
    -0.24
     Scale
    -0.24
     ALTER
    -0.24
    POSITIVE LOGITS
    é²ħ
    0.27
    oux
    0.27
    绸
    0.27
    rawl
    0.26
    æĦıè§ģåıįé¦Ī
    0.26
    AccessType
    0.26
    ulty
    0.25
    ioned
    0.25
    (rank
    0.24
     Strand
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.