© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 89756
    Prev
    Next
    INDEX
    Explanations

    resonance

    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
     cw
    -0.07
    就會
    -0.06
     Sommer
    -0.06
    Such
    -0.06
    同步
    -0.06
     ¡
    -0.06
     תת
    -0.06
    被誉
    -0.06
    vous
    -0.06
    .cl
    -0.06
    POSITIVE LOGITS
    ﴽ
    0.07
     Lite
    0.07
    _tab
    0.07
    _ylim
    0.07
    _last
    0.07
     potentials
    0.07
    标准
    0.07
    .TRAILING
    0.07
    펨
    0.07
    🗓
    0.07
    Activations Density 0.007%

    No Known Activations