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. 23-TRANSCODER-HP
    4. 2947
    Prev
    Next
    INDEX
    Explanations

    Time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    legg
    -0.30
    礴
    -0.28
    ä¸ĵåĪ©
    -0.26
    æ¯ıå¹´
    -0.26
     altern
    -0.26
     ImVec
    -0.25
    alement
    -0.25
    lation
    -0.25
    ourke
    -0.25
     salaries
    -0.25
    POSITIVE LOGITS
    ith
    0.29
    ish
    0.28
     attitude
    0.27
     before
    0.26
    och
    0.26
     Dating
    0.26
    ät
    0.26
    å°±å¼Ģå§ĭ
    0.25
    inner
    0.24
    öst
    0.24
    Activations Density 0.004%

    No Known Activations