© 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. 24227
    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
    ::-
    -0.28
    就好
    -0.27
     Mer
    -0.27
    åĨ»ç»ĵ
    -0.26
    ysis
    -0.26
    ffset
    -0.25
    ä¸įä¸Ģå®ļ
    -0.25
    âm
    -0.25
     Baker
    -0.24
    itect
    -0.23
    POSITIVE LOGITS
    ç¡ħ
    0.28
    roman
    0.27
    ovich
    0.26
     Meter
    0.25
    fty
    0.25
    rika
    0.25
    око
    0.25
    çĪ±å°Ķåħ°
    0.24
    _CAL
    0.24
    åİŁæĸĩ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.