© 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. 75395
    Prev
    Next
    INDEX
    Explanations

    virgin oil

    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
     Comp
    -0.08
     término
    -0.07
     Teddy
    -0.06
    э
    -0.06
    pełni
    -0.06
     fø
    -0.06
     Air
    -0.06
     assms
    -0.06
     Fill
    -0.06
     ż
    -0.06
    POSITIVE LOGITS
     spiritually
    0.08
    ')";↵
    0.07
     NSIndexPath
    0.07
     <<-
    0.07
    .wait
    0.07
    IBOutlet
    0.07
    	global
    0.07
    !important
    0.07
     UID
    0.07
    [...,
    0.07
    Activations Density 0.011%

    No Known Activations