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. 19-RESID-POST-AA
    6. 7544
    Prev
    Next
    INDEX
    Explanations

    period

    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
    	kfree
    -0.07
     printk
    -0.07
    ycin
    -0.07
    	strcat
    -0.07
    ئيس
    -0.07
    成長
    -0.07
    -manager
    -0.07
    requires
    -0.07
     memcpy
    -0.06
    startDate
    -0.06
    POSITIVE LOGITS
     çeşit
    0.07
    _Custom
    0.07
    我不想
    0.07
    Hash
    0.07
    亮点
    0.07
     Better
    0.06
    -conscious
    0.06
     фон
    0.06
    兆
    0.06
    Caption
    0.06
    Activations Density 0.215%

    No Known Activations