© 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. 15-RESID-POST-AA
    11. 79618
    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
     Snapshot
    -0.08
    annya
    -0.08
    köp
    -0.07
     cria
    -0.07
    貸
    -0.07
    _PEER
    -0.06
    .integration
    -0.06
     pkt
    -0.06
    pdata
    -0.06
     van
    -0.06
    POSITIVE LOGITS
    Areas
    0.07
    Opened
    0.07
    此案
    0.07
    GetWidth
    0.06
     Surv
    0.06
    sWith
    0.06
    	define
    0.06
    🐒
    0.06
     Rights
    0.06
     Adobe
    0.06
    Activations Density 0.011%

    No Known Activations