© 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. 88863
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    PerPixel
    -0.26
    :void
    -0.26
    :len
    -0.25
    lected
    -0.25
    }}},↵
    -0.25
    cba
    -0.24
    renc
    -0.24
    :Any
    -0.24
     пед
    -0.24
    icker
    -0.23
    POSITIVE LOGITS
    çļĦ羣å®ŀ
    0.28
    åıĪæĺ¯
    0.27
    羣å®ŀæĢ§
    0.26
    åľ°å¤Ħ
    0.26
     mans
    0.26
     intrinsic
    0.26
    èĢĥ
    0.25
    annah
    0.25
    ç²®
    0.25
     snaps
    0.25
    Activations Density 10.752%

    No Known Activations