© 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. 150178
    Prev
    Next
    INDEX
    Explanations

    after

    np_max-act-logits · gemini-2.0-flash
    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
    çłĶ究表æĺİ
    -0.41
     study
    -0.41
    study
    -0.37
    çłĶ究
    -0.35
     studies
    -0.35
    çłĶ究æĪIJæŀľ
    -0.35
    _study
    -0.34
    æľ¬æ¬¡
    -0.34
    æľ¬
    -0.34
    çļĦçłĶ究
    -0.33
    POSITIVE LOGITS
    ipherals
    0.28
    æŃ£åľ¨è¿Ľè¡Į
    0.25
    çķĻç»Ļ
    0.24
    chematic
    0.24
    utive
    0.24
    åĨįè§ģ
    0.24
    ãģĻãģĶ
    0.23
     lith
    0.23
    /target
    0.23
    åħ¨å¤©
    0.23
    Activations Density 1.364%

    No Known Activations