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. 15-RESID-POST-AA
    6. 56910
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seriously
    -0.07
    .steps
    -0.07
     khắc
    -0.07
    composite
    -0.07
    .ds
    -0.07
    esture
    -0.06
     teachings
    -0.06
    [cur
    -0.06
     באמת
    -0.06
     suck
    -0.06
    POSITIVE LOGITS
     Door
    0.08
     полов
    0.07
    퀀
    0.06
    她的
    0.06
     stanza
    0.06
    userID
    0.06
     Rw
    0.06
    מיקום
    0.06
    ⏠
    0.06
    errals
    0.06
    Activations Density 0.020%

    No Known Activations