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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56330
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     setMessage
    -0.07
     dank
    -0.07
     Desmond
    -0.07
     Leader
    -0.07
     בחדר
    -0.06
     Sleep
    -0.06
     gangbang
    -0.06
     Uns
    -0.06
    Ἷ
    -0.06
    ัว
    -0.06
    POSITIVE LOGITS
    можно
    0.08
    据报道
    0.07
     accumulate
    0.07
     الأمريكية
    0.07
    质量问题
    0.07
    Heavy
    0.07
     Arbitrary
    0.07
    ↵
    0.07
    ставить
    0.07
    Publish
    0.07
    Activations Density 0.000%

    No Known Activations