© 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. 18-TRANSCODER-HP
    7. 89681
    Prev
    Next
    INDEX
    Explanations

    programme descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĴéĢļ
    -0.29
    /MPL
    -0.27
    éĺ³åı°
    -0.27
     UPC
    -0.26
     informatie
    -0.26
    łģ
    -0.24
    item
    -0.24
    âİ¢
    -0.24
     onOptionsItemSelected
    -0.24
    ASS
    -0.24
    POSITIVE LOGITS
     Ded
    0.31
    oct
    0.30
    èĭ¦èĭ¦
    0.29
     aggrav
    0.26
     deduct
    0.26
    çģ«çĥŃ
    0.26
    StackSize
    0.25
     ded
    0.25
     marty
    0.25
     Cum
    0.25
    Activations Density 16.329%

    No Known Activations