© 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. 150307
    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
    sing
    -0.28
    eward
    -0.25
    TypeEnum
    -0.24
    第ä¸Ģ天
    -0.24
     removeFrom
    -0.23
    grams
    -0.23
    criptor
    -0.23
    ankan
    -0.23
    ubits
    -0.23
    ãĥ©ãĥ³ãĤŃãĥ³ãĤ°
    -0.23
    POSITIVE LOGITS
    ATUS
    0.25
     feedback
    0.24
     saÄŁlan
    0.24
    å¹´åĨħ
    0.23
    ä¸Ńåįİ
    0.23
    CONS
    0.23
    ée
    0.23
     treat
    0.23
    hoot
    0.22
     Fam
    0.22
    Activations Density 0.171%

    No Known Activations

    This feature has no known activations.