© 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. 19-RESID-POST-AA
    11. 4781
    Prev
    Next
    INDEX
    Explanations

    duck

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Silva
    -0.08
     Rodr
    -0.08
     fils
    -0.07
     spos
    -0.07
     Emil
    -0.07
    铂
    -0.07
    植树
    -0.07
    	MPI
    -0.07
    濠
    -0.07
    ophile
    -0.07
    POSITIVE LOGITS
     ducks
    0.08
    та
    0.08
    ТО
    0.07
    =#
    0.07
    YSTEM
    0.07
    like
    0.07
    stim
    0.07
    뗀
    0.07
    lifting
    0.07
    /modal
    0.07
    Activations Density 0.008%

    No Known Activations