© 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. 84798
    Prev
    Next
    INDEX
    Explanations

    0

    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
     불
    -0.08
     jm
    -0.07
    בוא
    -0.07
     Cv
    -0.07
    公认
    -0.07
    ('@
    -0.07
     Heal
    -0.07
    地震
    -0.07
    _re
    -0.07
     kak
    -0.07
    POSITIVE LOGITS
     entrenched
    0.08
    陉
    0.07
    mysqli
    0.07
    מסעדות
    0.07
    xEB
    0.07
     misrepresented
    0.07
     haunt
    0.07
     hinter
    0.06
    idunt
    0.06
    .rpc
    0.06
    Activations Density 0.001%

    No Known Activations