© 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 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. 15-RESID-POST-AA
    11. 83943
    Prev
    Next
    INDEX
    Explanations

    Code and data excerpts

    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_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
     poi
    -0.07
     getting
    -0.07
     need
    -0.07
    咦
    -0.06
     如
    -0.06
    _cond
    -0.06
     cuent
    -0.06
     press
    -0.06
    終
    -0.06
     forgive
    -0.06
    POSITIVE LOGITS
     gunfire
    0.08
    [layer
    0.07
    тради
    0.07
    Cols
    0.07
    出入
    0.07
    מלחמה
    0.07
    -)
    0.07
    odies
    0.07
    eler
    0.07
    万名
    0.07
    Activations Density 0.027%

    No Known Activations