© 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. 9463
    Prev
    Next
    INDEX
    Explanations

    ocean

    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
     wide
    -0.27
    -wide
    -0.26
    akis
    -0.26
     окÑĢÑĥ
    -0.25
    ACCEPT
    -0.25
    -workers
    -0.25
    \""
    -0.25
     members
    -0.24
    ComputedStyle
    -0.24
     }(
    -0.24
    POSITIVE LOGITS
    ause
    0.28
    åĪ·
    0.25
    bote
    0.25
    kich
    0.24
    паÑĢ
    0.24
    forward
    0.24
    å®ļ
    0.24
    apper
    0.23
    å¹²æ¶ī
    0.23
     Talent
    0.23
    Activations Density 0.904%

    No Known Activations