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. 72178
    Prev
    Next
    INDEX
    Explanations

    Launch

    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
    تخاذ
    -0.09
     cư
    -0.08
    打交道
    -0.08
     oluş
    -0.08
    💆
    -0.08
    ߜ
    -0.07
    _about
    -0.07
     PIO
    -0.07
     decorate
    -0.07
    비스
    -0.07
    POSITIVE LOGITS
    要求
    0.08
     HK
    0.07
    _comp
    0.07
     ABC
    0.07
    _H
    0.07
    ')}>↵
    0.07
    MM
    0.07
    的理由
    0.07
     jud
    0.07
    	var
    0.07
    Activations Density 0.000%

    No Known Activations