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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 5550
    Prev
    Next
    INDEX
    Explanations

    Scientific references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    亿吨
    -0.07
    (['/
    -0.07
    🗻
    -0.07
    人民政府
    -0.07
    UTE
    -0.07
    atory
    -0.07
    พลาด
    -0.07
    	sig
    -0.06
     $$$
    -0.06
     ديسمبر
    -0.06
    POSITIVE LOGITS
     İki
    0.07
    将领
    0.07
    -country
    0.07
    アウ
    0.07
     McGregor
    0.07
    齐
    0.07
     năm
    0.07
     واض
    0.06
    _FACT
    0.06
     RUNNING
    0.06
    Activations Density 0.019%

    No Known Activations