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. 88456
    Prev
    Next
    INDEX
    Explanations

    Research paper snippets

    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
    뗑
    -0.07
     Kes
    -0.07
    ⛲
    -0.07
    пуск
    -0.06
    ysz
    -0.06
     exchanged
    -0.06
     engaged
    -0.06
     saygı
    -0.06
    𝚟
    -0.06
    	Result
    -0.06
    POSITIVE LOGITS
    多达
    0.07
    olan
    0.07
    _pool
    0.07
     tab
    0.07
    激起
    0.07
    _UART
    0.07
    Hop
    0.07
    _orient
    0.06
     BILL
    0.06
     *↵↵↵
    0.06
    Activations Density 0.206%

    No Known Activations