© 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. 23-TRANSCODER-HP
    7. 24241
    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
    ars
    -0.34
    èľķ
    -0.30
    ARS
    -0.30
    çĭIJçĭ¸
    -0.28
    PFN
    -0.28
    ').'
    -0.26
    æ°ijåĽ½
    -0.26
    åĴ«
    -0.25
    imson
    -0.25
    缸åħ³è§Ħå®ļ
    -0.25
    POSITIVE LOGITS
    è£ģ
    0.30
    岸边
    0.27
    argon
    0.27
    ä¼ģåĽ¾
    0.27
    æĦŁ
    0.26
    岸
    0.25
     himself
    0.25
     premises
    0.25
    å¥īçĮ®
    0.25
    opup
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.