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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76060
    Prev
    Next
    INDEX
    Explanations

    mobility assistance/safety

    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
    "a
    -0.08
    十九大
    -0.07
    TEM
    -0.07
     Anyone
    -0.07
     handles
    -0.07
    大力发展
    -0.06
     Planet
    -0.06
    (article
    -0.06
     Thủ
    -0.06
    胗
    -0.06
    POSITIVE LOGITS
    江南
    0.07
     المشار
    0.07
    יקר
    0.06
     Consider
    0.06
    gay
    0.06
     מגיע
    0.06
    땁
    0.06
     Registr
    0.06
    .Room
    0.06
     bordel
    0.06
    Activations Density 0.480%

    No Known Activations