© 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. 11-RESID-POST-AA
    11. 76146
    Prev
    Next
    INDEX
    Explanations

    Lets

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ản
    -0.08
    	Action
    -0.07
    _DIFF
    -0.07
     Wage
    -0.07
    dration
    -0.07
    志愿服务
    -0.07
     Voyager
    -0.07
    劳动者
    -0.07
     Fire
    -0.07
    成员
    -0.07
    POSITIVE LOGITS
     trì
    0.08
    "]=>
    0.07
    reten
    0.07
    关于我们
    0.07
    características
    0.07
    .concatenate
    0.07
    ⟫
    0.07
    ▫
    0.07
     betting
    0.06
     breakfast
    0.06
    Activations Density 0.004%

    No Known Activations