© 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. 27-TRANSCODER-HP
    7. 58022
    Prev
    Next
    INDEX
    Explanations

    random text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīä½ķ
    -0.28
    dup
    -0.27
    岸
    -0.26
    å®īæİĴ
    -0.26
    è§Ħ
    -0.25
     segment
    -0.25
    InstanceState
    -0.25
     shore
    -0.25
     join
    -0.24
    å£ģçĶ»
    -0.24
    POSITIVE LOGITS
    istributor
    0.29
    uada
    0.29
    ierz
    0.28
    aised
    0.28
    éĢĤ
    0.28
    cação
    0.28
    osas
    0.27
    .Serve
    0.26
    apsible
    0.26
    ystone
    0.26
    Activations Density 0.011%

    No Known Activations