© 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. 7-RESID-POST-AA
    11. 77698
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _abstract
    -0.07
    Smart
    -0.07
     pam
    -0.07
    Porno
    -0.07
    _star
    -0.07
     abdomen
    -0.07
    _simulation
    -0.06
     solved
    -0.06
    细致
    -0.06
    保险公司
    -0.06
    POSITIVE LOGITS
     valu
    0.07
     tuned
    0.07
    더
    0.07
     which
    0.07
    中に
    0.07
    着
    0.07
    重温
    0.07
    able
    0.07
     alike
    0.06
    bers
    0.06
    Activations Density 0.007%

    No Known Activations