© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162657
    Prev
    Next
    INDEX
    Explanations

    Raw

    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
    esian
    -0.29
    áºĵ
    -0.26
    anza
    -0.26
    -0.25
    ozilla
    -0.25
    oser
    -0.25
    igner
    -0.24
    è¸ī
    -0.24
    dda
    -0.23
     saddle
    -0.23
    POSITIVE LOGITS
    /plain
    0.28
    é¦Ħ
    0.27
    æľ¬èº«å°±æĺ¯
    0.27
    HostException
    0.27
     Herc
    0.27
    mixed
    0.27
    å¤įåħ´
    0.26
    ä¸ŃåĽ½äººæ°ij
    0.26
    éĥĽ
    0.25
    rine
    0.25
    Activations Density 0.004%

    No Known Activations