© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    Code and license agreements

    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
    inged
    -0.30
    eer
    -0.28
    nesday
    -0.28
    epend
    -0.27
    tribution
    -0.26
    åijĺ
    -0.26
    alties
    -0.25
     workload
    -0.25
    agini
    -0.24
    ستاÙĨ
    -0.24
    POSITIVE LOGITS
     bast
    0.30
    bast
    0.26
    èĩªå·±åĸľæ¬¢
    0.26
    çļ±çº¹
    0.26
     opposite
    0.26
    IKE
    0.25
    ous
    0.25
    MethodImpl
    0.24
     undo
    0.24
    å¹²æ¶ī
    0.24
    Activations Density 0.003%

    No Known Activations