© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IKE
    -0.25
     PMC
    -0.24
     --↵
    -0.24
    æĭīå¼Ģ
    -0.24
    "":
    -0.24
    *time
    -0.23
    certificate
    -0.22
    kest
    -0.22
    ewise
    -0.22
    æĢİä¹ĪåĽŀäºĭ
    -0.22
    POSITIVE LOGITS
    atcher
    0.28
    ilk
    0.26
    èªī
    0.25
    asses
    0.25
    çĶµæ¢¯
    0.24
     acqu
    0.24
    æĻĶ
    0.24
    anded
    0.24
     pret
    0.23
    çŁ¥åIJį度
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.