© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 75140
    Prev
    Next
    INDEX
    Explanations

    technical forum questions

    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
     איש
    -0.07
    ○
    -0.07
     Ann
    -0.07
     Through
    -0.07
     mList
    -0.07
     under
    -0.07
    坋
    -0.07
     Tin
    -0.06
     Müller
    -0.06
    袯
    -0.06
    POSITIVE LOGITS
     veel
    0.08
     Logic
    0.07
    所说
    0.07
    sofar
    0.07
     confort
    0.07
    pcodes
    0.07
     ',
    0.07
     sẵn
    0.07
     overloaded
    0.06
     WC
    0.06
    Activations Density 0.442%

    No Known Activations