© 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. 11-RESID-POST-AA
    11. 152
    Prev
    Next
    INDEX
    Explanations

    space

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stopwatch
    -0.07
    ह
    -0.07
     afterward
    -0.07
    .man
    -0.06
    祈
    -0.06
     איל
    -0.06
    .Def
    -0.06
    (nameof
    -0.06
    ಚ
    -0.06
     subscription
    -0.06
    POSITIVE LOGITS
    ustering
    0.08
    是你
    0.07
     intimate
    0.07
    _dst
    0.07
    不过是
    0.07
     together
    0.07
     Romance
    0.07
     RID
    0.07
    踏入
    0.07
    和他的
    0.07
    Activations Density 0.020%

    No Known Activations