© 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. 85897
    Prev
    Next
    INDEX
    Explanations

    $\stackrel{d}{\to}$

    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
     Bs
    -0.07
    (short
    -0.07
    sistência
    -0.07
     Mormons
    -0.07
    	z
    -0.07
     ((*
    -0.07
     Amer
    -0.07
    (tf
    -0.07
     ghost
    -0.07
     amd
    -0.07
    POSITIVE LOGITS
    ъ
    0.07
    连云
    0.07
     piled
    0.07
    Ễ
    0.07
     Particle
    0.07
     hủy
    0.07
     sloppy
    0.07
    飞机
    0.07
     nadzie
    0.07
     الحوار
    0.07
    Activations Density 0.008%

    No Known Activations