Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46764
    Prev
    Next
    INDEX
    Explanations

    worldwide events/issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leÅŁ
    -0.27
    转åŀĭåıijå±ķ
    -0.26
    achi
    -0.25
     inertia
    -0.25
    ||(
    -0.25
     unins
    -0.25
     inert
    -0.25
     hardest
    -0.24
    croft
    -0.24
    Ħä»¶
    -0.24
    POSITIVE LOGITS
    mos
    0.32
    CORD
    0.28
     mong
    0.26
    éĢ
    0.26
    roller
    0.25
    å¡ĺ
    0.25
    defs
    0.24
    ToArray
    0.24
    èĦĤ
    0.24
    éŃĶ鬼
    0.24
    Activations Density 0.008%

    No Known Activations