© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27277
    Prev
    Next
    INDEX
    Explanations

    Legal codes/references

    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
     réserve
    -0.07
    ≓
    -0.07
    不同
    -0.07
    ibe
    -0.06
     forbidden
    -0.06
     ""){↵
    -0.06
    ื่
    -0.06
    泪水
    -0.06
    不已
    -0.06
    ホ
    -0.06
    POSITIVE LOGITS
    .TextInput
    0.08
    ascade
    0.07
     Metal
    0.07
     HUD
    0.07
     Triumph
    0.07
    -generation
    0.07
    仿
    0.07
     projeto
    0.07
    -with
    0.07
    INATION
    0.07
    Activations Density 0.005%

    No Known Activations