© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 109691
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    gio
    -0.08
    苏宁
    -0.08
    薁
    -0.07
    ject
    -0.07
    滘
    -0.07
    ipe
    -0.07
     bleed
    -0.07
    溇
    -0.07
    (nodes
    -0.07
    iasco
    -0.07
    POSITIVE LOGITS
    privacy
    0.07
     primitive
    0.07
    ,param
    0.07
     complicated
    0.07
     mentally
    0.07
     sincer
    0.07
    	d
    0.07
     explode
    0.07
    裁定
    0.07
    (configuration
    0.07
    Activations Density 0.132%

    No Known Activations