© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    symmetry

    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
     buffet
    -0.27
    çĦ¦çĤ¹
    -0.26
     mound
    -0.26
     whisky
    -0.26
     prox
    -0.25
     Shape
    -0.25
    èµ·æĿ¥
    -0.24
    ç¦Ĭ
    -0.24
    çķıæĥ§
    -0.24
    ç£ħ
    -0.24
    POSITIVE LOGITS
    occan
    0.26
    æ¯ĶåĪ©
    0.26
    -Cs
    0.26
    lij
    0.24
    ISO
    0.24
    adoo
    0.24
    .nativeElement
    0.24
    @g
    0.24
    apl
    0.24
    èĢĹ
    0.24
    Activations Density 0.008%

    No Known Activations