© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 7365
    Prev
    Next
    INDEX
    Explanations

    called

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Desc
    -0.07
     rewarding
    -0.07
     ends
    -0.07
    MIN
    -0.06
    	cmd
    -0.06
    连续
    -0.06
     Colomb
    -0.06
     depressed
    -0.06
     exhibited
    -0.06
    Day
    -0.06
    POSITIVE LOGITS
     Forms
    0.08
    �
    0.07
    ...">↵
    0.07
    ')+
    0.07
    ハン
    0.07
    出现了
    0.07
    )";↵↵
    0.07
     została
    0.06
     `}↵
    0.06
    ்
    0.06
    Activations Density 1.260%

    No Known Activations