© 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. 70868
    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
    堅
    -0.07
     identical
    -0.06
    列举
    -0.06
     persuade
    -0.06
    (Cl
    -0.06
    降落
    -0.06
    ánt
    -0.06
    termin
    -0.06
    pearance
    -0.06
    stricted
    -0.06
    POSITIVE LOGITS
     Lua
    0.08
     FB
    0.07
     WINDOWS
    0.07
    라면
    0.07
    老人
    0.07
     Spaces
    0.07
     framebuffer
    0.07
     Encounter
    0.07
     לבצע
    0.07
    Ground
    0.06
    Activations Density 0.015%

    No Known Activations