Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 72433
    Prev
    Next
    INDEX
    Explanations

    are

    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
    隋
    -0.07
    汛
    -0.07
    集市
    -0.07
     Lastly
    -0.07
    _Equals
    -0.07
    十里
    -0.07
     }↵↵↵↵↵↵
    -0.06
     Cartoon
    -0.06
     sentiment
    -0.06
    ocio
    -0.06
    POSITIVE LOGITS
    gan
    0.07
     refere
    0.07
     lifes
    0.07
     바
    0.07
    azed
    0.06
    巴斯
    0.06
    kul
    0.06
     Advoc
    0.06
    ecome
    0.06
     Dop
    0.06
    Activations Density 0.099%

    No Known Activations