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. 130280
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     qua
    -0.08
    她在
    -0.07
    usi
    -0.07
    十分钟
    -0.07
    它可以
    -0.07
    élection
    -0.07
    icht
    -0.07
    都应该
    -0.07
    ลอง
    -0.06
    ⼤
    -0.06
    POSITIVE LOGITS
    	rm
    0.08
     raping
    0.08
    _Err
    0.07
     Game
    0.07
    九大精神
    0.07
    Div
    0.07
    estic
    0.07
     dual
    0.07
    FileManager
    0.06
    幅
    0.06
    Activations Density 0.005%

    No Known Activations