© 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. 8569
    Prev
    Next
    INDEX
    Explanations

    Z

    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
    åĩĨ
    -0.33
     outward
    -0.24
    outh
    -0.24
     davran
    -0.23
    itious
    -0.23
    bserv
    -0.22
    å¦Ĥæľīä¾µæĿĥ
    -0.22
    .complete
    -0.22
     colle
    -0.22
     Prec
    -0.22
    POSITIVE LOGITS
    =z
    0.35
    ephy
    0.33
    (z
    0.33
    abbix
    0.33
    [z
    0.30
    illions
    0.30
    /z
    0.30
    eros
    0.28
    zag
    0.28
    *z
    0.28
    Activations Density 0.166%

    No Known Activations