© 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. 30-TRANSCODER-HP
    7. 95623
    Prev
    Next
    INDEX
    Explanations

    Legal, university, or code texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hardware
    -0.28
    线
    -0.27
    Hardware
    -0.25
     Handy
    -0.25
    åŃĿ
    -0.24
     linear
    -0.24
     short
    -0.24
     liner
    -0.24
    reat
    -0.23
    ias
    -0.23
    POSITIVE LOGITS
    amentals
    0.32
    arged
    0.29
    侬
    0.28
    neys
    0.28
    åĴĮåıijå±ķ
    0.27
    /copyleft
    0.27
     Reyes
    0.26
    DEM
    0.26
    pone
    0.25
    meldung
    0.25
    Activations Density 0.783%

    No Known Activations