© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 45182
    Prev
    Next
    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vend
    -0.07
     accidental
    -0.07
     fer
    -0.07
     moisture
    -0.07
    نفذ
    -0.07
     painful
    -0.07
     sunny
    -0.06
     difficile
    -0.06
     najle
    -0.06
    .cell
    -0.06
    POSITIVE LOGITS
    (ROOT
    0.07
    读后
    0.07
    快餐
    0.07
    结合起来
    0.07
    绿化
    0.07
    歷
    0.07
    动漫
    0.07
    ຕ
    0.06
    配套
    0.06
    测算
    0.06
    Activations Density 0.195%

    No Known Activations