© 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. 23-RESID-POST-AA
    6. 713
    Prev
    Next
    INDEX
    Explanations

    Jan

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    北京市
    -0.07
    ∘
    -0.07
     Virt
    -0.07
    MAS
    -0.06
    CppGenericClass
    -0.06
    Py
    -0.06
    ADC
    -0.06
    !!.
    -0.06
     SUBJECT
    -0.06
    /")↵
    -0.06
    POSITIVE LOGITS
    بذل
    0.08
    护理
    0.07
    .requires
    0.07
     htmlFor
    0.07
    追逐
    0.07
    ȥ
    0.07
    żenia
    0.07
    ヲ
    0.07
    عزل
    0.06
    研究报告
    0.06
    Activations Density 0.008%

    No Known Activations