© 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. 24830
    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
    VIS
    -0.28
    æŃ£å®Ĺ
    -0.27
     Bor
    -0.27
    CRT
    -0.27
    被æ·ĺæ±°
    -0.26
    ArgsConstructor
    -0.26
    .NewRequest
    -0.26
    ÑħодиÑĤ
    -0.25
    Pin
    -0.25
    天é¹ħ
    -0.25
    POSITIVE LOGITS
     layouts
    0.30
    éĭª
    0.27
     stre
    0.26
     plans
    0.26
    gard
    0.25
     st
    0.24
    æŃĩ
    0.24
     Layout
    0.24
    nett
    0.24
     statusCode
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.